David Pomerenke
commited on
Commit
·
86b8b3a
1
Parent(s):
49ffc1d
Add bert_score evaluation
Browse files- index.html +13 -11
- languagebench.py +26 -16
- pyproject.toml +1 -0
- results.json +514 -274
- results_summary.json +400 -195
- uv.lock +0 -0
index.html
CHANGED
@@ -35,12 +35,14 @@
|
|
35 |
import * as Plot from "https://cdn.jsdelivr.net/npm/@observablehq/plot@0.6/+esm";
|
36 |
|
37 |
async function init() {
|
|
|
|
|
38 |
const chartsDiv = document.getElementById('charts');
|
39 |
|
40 |
const summary = await fetch('results_summary.json');
|
41 |
const summaryData = await summary.json();
|
42 |
// Format captions
|
43 |
-
const formatTitle = d => d.target_language_name + "\n" + parseInt(d.speakers / 1_000_00) / 10 + "M speakers\
|
44 |
|
45 |
// Create summary plot
|
46 |
const summaryPlot = Plot.plot({
|
@@ -48,29 +50,29 @@
|
|
48 |
height: 400,
|
49 |
marginBottom: 100,
|
50 |
x: { label: "Number of speakers", axis: null },
|
51 |
-
y: { label:
|
52 |
// color: { scheme: "BrBG" },
|
53 |
marks: [
|
54 |
Plot.rectY(summaryData, Plot.stackX({
|
55 |
x: "speakers",
|
56 |
-
order:
|
57 |
reverse: true,
|
58 |
-
y2:
|
59 |
title: formatTitle,
|
60 |
tip: true,
|
61 |
// fill: d => -d.bleu
|
62 |
})),
|
63 |
Plot.rectY(summaryData, Plot.pointerX(Plot.stackX({
|
64 |
x: "speakers",
|
65 |
-
order:
|
66 |
reverse: true,
|
67 |
-
y2:
|
68 |
fill: "grey",
|
69 |
}))),
|
70 |
Plot.text(summaryData, Plot.stackX({
|
71 |
x: "speakers",
|
72 |
-
y2:
|
73 |
-
order:
|
74 |
reverse: true,
|
75 |
text: "target_language_name",
|
76 |
frameAnchor: "bottom",
|
@@ -135,13 +137,13 @@
|
|
135 |
height: 200,
|
136 |
margin: 30,
|
137 |
y: {
|
138 |
-
domain: [0,
|
139 |
-
label:
|
140 |
},
|
141 |
marks: [
|
142 |
Plot.barY(languageData, {
|
143 |
x: d => descriptor(d.model),
|
144 |
-
y:
|
145 |
})
|
146 |
]
|
147 |
});
|
|
|
35 |
import * as Plot from "https://cdn.jsdelivr.net/npm/@observablehq/plot@0.6/+esm";
|
36 |
|
37 |
async function init() {
|
38 |
+
const scoreKey = "bleu"
|
39 |
+
const scoreName = "BLEU Score"
|
40 |
const chartsDiv = document.getElementById('charts');
|
41 |
|
42 |
const summary = await fetch('results_summary.json');
|
43 |
const summaryData = await summary.json();
|
44 |
// Format captions
|
45 |
+
const formatTitle = d => (d.target_language_name + "\n" + parseInt(d.speakers / 1_000_00) / 10 + "M speakers\n" + scoreName + ": " + d[scoreKey].toFixed(1))
|
46 |
|
47 |
// Create summary plot
|
48 |
const summaryPlot = Plot.plot({
|
|
|
50 |
height: 400,
|
51 |
marginBottom: 100,
|
52 |
x: { label: "Number of speakers", axis: null },
|
53 |
+
y: { label: `${scoreName} (average across models)` },
|
54 |
// color: { scheme: "BrBG" },
|
55 |
marks: [
|
56 |
Plot.rectY(summaryData, Plot.stackX({
|
57 |
x: "speakers",
|
58 |
+
order: scoreKey,
|
59 |
reverse: true,
|
60 |
+
y2: scoreKey, // y2 to avoid stacking by y
|
61 |
title: formatTitle,
|
62 |
tip: true,
|
63 |
// fill: d => -d.bleu
|
64 |
})),
|
65 |
Plot.rectY(summaryData, Plot.pointerX(Plot.stackX({
|
66 |
x: "speakers",
|
67 |
+
order: scoreKey,
|
68 |
reverse: true,
|
69 |
+
y2: scoreKey, // y2 to avoid stacking by y
|
70 |
fill: "grey",
|
71 |
}))),
|
72 |
Plot.text(summaryData, Plot.stackX({
|
73 |
x: "speakers",
|
74 |
+
y2: scoreKey,
|
75 |
+
order: scoreKey,
|
76 |
reverse: true,
|
77 |
text: "target_language_name",
|
78 |
frameAnchor: "bottom",
|
|
|
137 |
height: 200,
|
138 |
margin: 30,
|
139 |
y: {
|
140 |
+
domain: [0, 1],
|
141 |
+
label: scoreName
|
142 |
},
|
143 |
marks: [
|
144 |
Plot.barY(languageData, {
|
145 |
x: d => descriptor(d.model),
|
146 |
+
y: scoreKey
|
147 |
})
|
148 |
]
|
149 |
});
|
languagebench.py
CHANGED
@@ -37,9 +37,23 @@ client = AsyncOpenAI(
|
|
37 |
)
|
38 |
cache = Memory(location=".cache", verbose=0).cache
|
39 |
bleu = evaluate.load("sacrebleu")
|
|
|
40 |
rate_limit = AsyncLimiter(max_rate=15, time_period=1)
|
41 |
|
42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
def check_rate_limit():
|
44 |
print(
|
45 |
requests.get(
|
@@ -64,18 +78,6 @@ async def complete(**kwargs):
|
|
64 |
return response
|
65 |
|
66 |
|
67 |
-
def reorder(language_name):
|
68 |
-
if "," in language_name and "(" not in language_name:
|
69 |
-
return language_name.split(",")[1] + " " + language_name.split(",")[0]
|
70 |
-
return language_name
|
71 |
-
|
72 |
-
|
73 |
-
language_names = pd.read_csv("LanguageCodes.tab", sep="\t")
|
74 |
-
language_names["Name"] = language_names["Name"].apply(reorder)
|
75 |
-
language_stats = pd.read_csv("languages.tsv", sep="\t")
|
76 |
-
script_names = pd.read_csv("ScriptCodes.csv")
|
77 |
-
|
78 |
-
|
79 |
@cache
|
80 |
async def translate(model, target_language, target_script, sentence):
|
81 |
reply = await complete(
|
@@ -112,13 +114,16 @@ def get_language_stats(language_code):
|
|
112 |
return stats
|
113 |
|
114 |
|
|
|
|
|
|
|
|
|
|
|
115 |
async def main():
|
116 |
n = 30
|
117 |
results = []
|
118 |
original_sentences = open(f"{dataset}/dev.{original_language}").readlines()
|
119 |
for target_language in target_languages:
|
120 |
-
if target_language == original_language:
|
121 |
-
continue
|
122 |
target_sentences = open(f"{dataset}/dev.{target_language}").readlines()
|
123 |
for model in models:
|
124 |
if model != fast_model and target_language not in detailed_target_languages:
|
@@ -135,7 +140,11 @@ async def main():
|
|
135 |
references=target_sentences[:n],
|
136 |
tokenize="char",
|
137 |
)
|
138 |
-
|
|
|
|
|
|
|
|
|
139 |
results.append(
|
140 |
{
|
141 |
"model": model,
|
@@ -144,12 +153,13 @@ async def main():
|
|
144 |
"target_language_name": stats["name"],
|
145 |
"speakers": int(stats.get("maxSpeakers", 0)),
|
146 |
"bleu": metrics["score"],
|
|
|
147 |
}
|
148 |
)
|
149 |
with open("results.json", "w") as f:
|
150 |
json.dump(results, f, indent=2, ensure_ascii=False)
|
151 |
pd.DataFrame(results).groupby("target_language_name").agg(
|
152 |
-
{"bleu": "mean", "speakers": "mean"}
|
153 |
).reset_index().to_json("results_summary.json", indent=2, orient="records")
|
154 |
|
155 |
|
|
|
37 |
)
|
38 |
cache = Memory(location=".cache", verbose=0).cache
|
39 |
bleu = evaluate.load("sacrebleu")
|
40 |
+
bertscore = evaluate.load("bertscore")
|
41 |
rate_limit = AsyncLimiter(max_rate=15, time_period=1)
|
42 |
|
43 |
|
44 |
+
def reorder(language_name):
|
45 |
+
if "," in language_name and "(" not in language_name:
|
46 |
+
return language_name.split(",")[1] + " " + language_name.split(",")[0]
|
47 |
+
return language_name
|
48 |
+
|
49 |
+
|
50 |
+
language_names = pd.read_csv("LanguageCodes.tab", sep="\t")
|
51 |
+
language_names["Name"] = language_names["Name"].apply(reorder).str.strip()
|
52 |
+
language_stats = pd.read_csv("languages.tsv", sep="\t")
|
53 |
+
script_names = pd.read_csv("ScriptCodes.csv")
|
54 |
+
|
55 |
+
|
56 |
+
# utils
|
57 |
def check_rate_limit():
|
58 |
print(
|
59 |
requests.get(
|
|
|
78 |
return response
|
79 |
|
80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
@cache
|
82 |
async def translate(model, target_language, target_script, sentence):
|
83 |
reply = await complete(
|
|
|
114 |
return stats
|
115 |
|
116 |
|
117 |
+
def mean(l):
|
118 |
+
return sum(l) / len(l)
|
119 |
+
|
120 |
+
|
121 |
+
# evaluation!
|
122 |
async def main():
|
123 |
n = 30
|
124 |
results = []
|
125 |
original_sentences = open(f"{dataset}/dev.{original_language}").readlines()
|
126 |
for target_language in target_languages:
|
|
|
|
|
127 |
target_sentences = open(f"{dataset}/dev.{target_language}").readlines()
|
128 |
for model in models:
|
129 |
if model != fast_model and target_language not in detailed_target_languages:
|
|
|
140 |
references=target_sentences[:n],
|
141 |
tokenize="char",
|
142 |
)
|
143 |
+
bert_metrics = bertscore.compute(
|
144 |
+
predictions=predictions,
|
145 |
+
references=target_sentences[:n],
|
146 |
+
model_type="distilbert-base-uncased",
|
147 |
+
)
|
148 |
results.append(
|
149 |
{
|
150 |
"model": model,
|
|
|
153 |
"target_language_name": stats["name"],
|
154 |
"speakers": int(stats.get("maxSpeakers", 0)),
|
155 |
"bleu": metrics["score"],
|
156 |
+
"bert_score": mean(bert_metrics["f1"]),
|
157 |
}
|
158 |
)
|
159 |
with open("results.json", "w") as f:
|
160 |
json.dump(results, f, indent=2, ensure_ascii=False)
|
161 |
pd.DataFrame(results).groupby("target_language_name").agg(
|
162 |
+
{"bleu": "mean", "bert_score": "mean", "speakers": "mean"}
|
163 |
).reset_index().to_json("results_summary.json", indent=2, orient="records")
|
164 |
|
165 |
|
pyproject.toml
CHANGED
@@ -6,6 +6,7 @@ readme = "README.md"
|
|
6 |
requires-python = ">=3.10"
|
7 |
dependencies = [
|
8 |
"aiolimiter>=1.1.0",
|
|
|
9 |
"evaluate>=0.4.3",
|
10 |
"joblib>=1.4.2",
|
11 |
"openai>=1.52.2",
|
|
|
6 |
requires-python = ">=3.10"
|
7 |
dependencies = [
|
8 |
"aiolimiter>=1.1.0",
|
9 |
+
"bert-score>=0.3.13",
|
10 |
"evaluate>=0.4.3",
|
11 |
"joblib>=1.4.2",
|
12 |
"openai>=1.52.2",
|
results.json
CHANGED
@@ -5,15 +5,17 @@
|
|
5 |
"target_language": "tur_Latn",
|
6 |
"target_language_name": "Turkish",
|
7 |
"speakers": 82231620,
|
8 |
-
"bleu": 67.16006256755001
|
|
|
9 |
},
|
10 |
{
|
11 |
"model": "anthropic/claude-3.5-sonnet",
|
12 |
"original_language": "eng_Latn",
|
13 |
"target_language": "ary_Arab",
|
14 |
-
"target_language_name": "
|
15 |
"speakers": 27500000,
|
16 |
-
"bleu":
|
|
|
17 |
},
|
18 |
{
|
19 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -21,7 +23,8 @@
|
|
21 |
"target_language": "fij_Latn",
|
22 |
"target_language_name": "Fijian",
|
23 |
"speakers": 341270,
|
24 |
-
"bleu": 58.28926672457303
|
|
|
25 |
},
|
26 |
{
|
27 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -29,7 +32,8 @@
|
|
29 |
"target_language": "lug_Latn",
|
30 |
"target_language_name": "Ganda",
|
31 |
"speakers": 4100000,
|
32 |
-
"bleu": 45.86933229358203
|
|
|
33 |
},
|
34 |
{
|
35 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -37,7 +41,8 @@
|
|
37 |
"target_language": "kin_Latn",
|
38 |
"target_language_name": "Kinyarwanda",
|
39 |
"speakers": 12100000,
|
40 |
-
"bleu": 57.241062675597036
|
|
|
41 |
},
|
42 |
{
|
43 |
"model": "openai/gpt-4o-mini",
|
@@ -45,7 +50,8 @@
|
|
45 |
"target_language": "ind_Latn",
|
46 |
"target_language_name": "Indonesian",
|
47 |
"speakers": 198996550,
|
48 |
-
"bleu": 76.69607051201163
|
|
|
49 |
},
|
50 |
{
|
51 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -53,7 +59,8 @@
|
|
53 |
"target_language": "ind_Latn",
|
54 |
"target_language_name": "Indonesian",
|
55 |
"speakers": 198996550,
|
56 |
-
"bleu": 75.20007995551391
|
|
|
57 |
},
|
58 |
{
|
59 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
@@ -61,7 +68,8 @@
|
|
61 |
"target_language": "ind_Latn",
|
62 |
"target_language_name": "Indonesian",
|
63 |
"speakers": 198996550,
|
64 |
-
"bleu": 74.1959714053824
|
|
|
65 |
},
|
66 |
{
|
67 |
"model": "mistralai/mistral-nemo",
|
@@ -69,7 +77,8 @@
|
|
69 |
"target_language": "ind_Latn",
|
70 |
"target_language_name": "Indonesian",
|
71 |
"speakers": 198996550,
|
72 |
-
"bleu": 65.59558256613556
|
|
|
73 |
},
|
74 |
{
|
75 |
"model": "qwen/qwen-2.5-72b-instruct",
|
@@ -77,7 +86,8 @@
|
|
77 |
"target_language": "ind_Latn",
|
78 |
"target_language_name": "Indonesian",
|
79 |
"speakers": 198996550,
|
80 |
-
"bleu": 72.85582869172275
|
|
|
81 |
},
|
82 |
{
|
83 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -85,7 +95,8 @@
|
|
85 |
"target_language": "nus_Latn",
|
86 |
"target_language_name": "Nuer",
|
87 |
"speakers": 900000,
|
88 |
-
"bleu": 16.57969879511241
|
|
|
89 |
},
|
90 |
{
|
91 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -93,23 +104,26 @@
|
|
93 |
"target_language": "szl_Latn",
|
94 |
"target_language_name": "Silesian",
|
95 |
"speakers": 522000,
|
96 |
-
"bleu": 56.78363920686616
|
|
|
97 |
},
|
98 |
{
|
99 |
"model": "anthropic/claude-3.5-sonnet",
|
100 |
"original_language": "eng_Latn",
|
101 |
"target_language": "azj_Latn",
|
102 |
-
"target_language_name": "
|
103 |
"speakers": 9220610,
|
104 |
-
"bleu": 55.
|
|
|
105 |
},
|
106 |
{
|
107 |
"model": "anthropic/claude-3.5-sonnet",
|
108 |
"original_language": "eng_Latn",
|
109 |
"target_language": "dik_Latn",
|
110 |
-
"target_language_name": "
|
111 |
"speakers": 0,
|
112 |
-
"bleu":
|
|
|
113 |
},
|
114 |
{
|
115 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -117,7 +131,8 @@
|
|
117 |
"target_language": "smo_Latn",
|
118 |
"target_language_name": "Samoan",
|
119 |
"speakers": 415720,
|
120 |
-
"bleu": 56.71388314225869
|
|
|
121 |
},
|
122 |
{
|
123 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -125,7 +140,8 @@
|
|
125 |
"target_language": "heb_Hebr",
|
126 |
"target_language_name": "Hebrew",
|
127 |
"speakers": 9303950,
|
128 |
-
"bleu": 72.0702990513479
|
|
|
129 |
},
|
130 |
{
|
131 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -133,7 +149,8 @@
|
|
133 |
"target_language": "lao_Laoo",
|
134 |
"target_language_name": "Lao",
|
135 |
"speakers": 5225552,
|
136 |
-
"bleu": 60.02109096770294
|
|
|
137 |
},
|
138 |
{
|
139 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -141,7 +158,8 @@
|
|
141 |
"target_language": "bul_Cyrl",
|
142 |
"target_language_name": "Bulgarian",
|
143 |
"speakers": 9000000,
|
144 |
-
"bleu": 72.9695925130979
|
|
|
145 |
},
|
146 |
{
|
147 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -149,7 +167,8 @@
|
|
149 |
"target_language": "dgo_Deva",
|
150 |
"target_language_name": "Dogri",
|
151 |
"speakers": 2000000,
|
152 |
-
"bleu": 44.91535352779186
|
|
|
153 |
},
|
154 |
{
|
155 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -157,15 +176,17 @@
|
|
157 |
"target_language": "epo_Latn",
|
158 |
"target_language_name": "Esperanto",
|
159 |
"speakers": 2000000,
|
160 |
-
"bleu": 69.60565775541012
|
|
|
161 |
},
|
162 |
{
|
163 |
"model": "anthropic/claude-3.5-sonnet",
|
164 |
"original_language": "eng_Latn",
|
165 |
"target_language": "azb_Arab",
|
166 |
-
"target_language_name": "
|
167 |
"speakers": 15000000,
|
168 |
-
"bleu":
|
|
|
169 |
},
|
170 |
{
|
171 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -173,7 +194,8 @@
|
|
173 |
"target_language": "pap_Latn",
|
174 |
"target_language_name": "Papiamentu",
|
175 |
"speakers": 321300,
|
176 |
-
"bleu": 69.79553281331113
|
|
|
177 |
},
|
178 |
{
|
179 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -181,7 +203,8 @@
|
|
181 |
"target_language": "ces_Latn",
|
182 |
"target_language_name": "Czech",
|
183 |
"speakers": 10700000,
|
184 |
-
"bleu": 69.71122905993063
|
|
|
185 |
},
|
186 |
{
|
187 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -189,7 +212,8 @@
|
|
189 |
"target_language": "gle_Latn",
|
190 |
"target_language_name": "Irish",
|
191 |
"speakers": 1030000,
|
192 |
-
"bleu": 69.97251945242859
|
|
|
193 |
},
|
194 |
{
|
195 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -197,7 +221,8 @@
|
|
197 |
"target_language": "cym_Latn",
|
198 |
"target_language_name": "Welsh",
|
199 |
"speakers": 977366,
|
200 |
-
"bleu": 83.34377244735965
|
|
|
201 |
},
|
202 |
{
|
203 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -205,7 +230,8 @@
|
|
205 |
"target_language": "war_Latn",
|
206 |
"target_language_name": "Waray-Waray",
|
207 |
"speakers": 3100000,
|
208 |
-
"bleu": 66.38502312428538
|
|
|
209 |
},
|
210 |
{
|
211 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -213,7 +239,8 @@
|
|
213 |
"target_language": "tuk_Latn",
|
214 |
"target_language_name": "Turkmen",
|
215 |
"speakers": 16000000,
|
216 |
-
"bleu": 60.559370593640274
|
|
|
217 |
},
|
218 |
{
|
219 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -221,7 +248,8 @@
|
|
221 |
"target_language": "kea_Latn",
|
222 |
"target_language_name": "Kabuverdianu",
|
223 |
"speakers": 871000,
|
224 |
-
"bleu": 65.11060103907447
|
|
|
225 |
},
|
226 |
{
|
227 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -229,7 +257,8 @@
|
|
229 |
"target_language": "swe_Latn",
|
230 |
"target_language_name": "Swedish",
|
231 |
"speakers": 9244250,
|
232 |
-
"bleu": 77.42161024703672
|
|
|
233 |
},
|
234 |
{
|
235 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -237,7 +266,8 @@
|
|
237 |
"target_language": "mni_Mtei",
|
238 |
"target_language_name": "Meitei",
|
239 |
"speakers": 1470000,
|
240 |
-
"bleu": 41.90750872077243
|
|
|
241 |
},
|
242 |
{
|
243 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -245,15 +275,17 @@
|
|
245 |
"target_language": "kan_Knda",
|
246 |
"target_language_name": "Kannada",
|
247 |
"speakers": 43600000,
|
248 |
-
"bleu": 60.01420283321725
|
|
|
249 |
},
|
250 |
{
|
251 |
"model": "anthropic/claude-3.5-sonnet",
|
252 |
"original_language": "eng_Latn",
|
253 |
"target_language": "plt_Latn",
|
254 |
-
"target_language_name": "
|
255 |
"speakers": 0,
|
256 |
-
"bleu":
|
|
|
257 |
},
|
258 |
{
|
259 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -261,7 +293,8 @@
|
|
261 |
"target_language": "ewe_Latn",
|
262 |
"target_language_name": "Éwé",
|
263 |
"speakers": 3000000,
|
264 |
-
"bleu": 41.6614038790914
|
|
|
265 |
},
|
266 |
{
|
267 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -269,7 +302,8 @@
|
|
269 |
"target_language": "rus_Cyrl",
|
270 |
"target_language_name": "Russian",
|
271 |
"speakers": 171428900,
|
272 |
-
"bleu": 71.14894410390329
|
|
|
273 |
},
|
274 |
{
|
275 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -277,7 +311,8 @@
|
|
277 |
"target_language": "bjn_Arab",
|
278 |
"target_language_name": "Banjar",
|
279 |
"speakers": 3500000,
|
280 |
-
"bleu": 36.7812759423696
|
|
|
281 |
},
|
282 |
{
|
283 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -285,7 +320,8 @@
|
|
285 |
"target_language": "kmb_Latn",
|
286 |
"target_language_name": "Kimbundu",
|
287 |
"speakers": 0,
|
288 |
-
"bleu": 5.85234572235619
|
|
|
289 |
},
|
290 |
{
|
291 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -293,15 +329,17 @@
|
|
293 |
"target_language": "vec_Latn",
|
294 |
"target_language_name": "Venetian",
|
295 |
"speakers": 2000000,
|
296 |
-
"bleu": 60.61408762705794
|
|
|
297 |
},
|
298 |
{
|
299 |
"model": "anthropic/claude-3.5-sonnet",
|
300 |
"original_language": "eng_Latn",
|
301 |
"target_language": "aeb_Arab",
|
302 |
-
"target_language_name": "
|
303 |
"speakers": 11600000,
|
304 |
-
"bleu": 49.
|
|
|
305 |
},
|
306 |
{
|
307 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -309,7 +347,8 @@
|
|
309 |
"target_language": "lit_Latn",
|
310 |
"target_language_name": "Lithuanian",
|
311 |
"speakers": 4000000,
|
312 |
-
"bleu": 67.16256955707802
|
|
|
313 |
},
|
314 |
{
|
315 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -317,7 +356,8 @@
|
|
317 |
"target_language": "swh_Latn",
|
318 |
"target_language_name": "Swahili",
|
319 |
"speakers": 82300000,
|
320 |
-
"bleu": 73.51990421418041
|
|
|
321 |
},
|
322 |
{
|
323 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -325,15 +365,17 @@
|
|
325 |
"target_language": "bug_Latn",
|
326 |
"target_language_name": "Bugis",
|
327 |
"speakers": 5017800,
|
328 |
-
"bleu": 44.838817003109384
|
|
|
329 |
},
|
330 |
{
|
331 |
"model": "anthropic/claude-3.5-sonnet",
|
332 |
"original_language": "eng_Latn",
|
333 |
"target_language": "apc_Arab_nort3139",
|
334 |
-
"target_language_name": "
|
335 |
"speakers": 44000000,
|
336 |
-
"bleu":
|
|
|
337 |
},
|
338 |
{
|
339 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -341,7 +383,8 @@
|
|
341 |
"target_language": "lus_Latn",
|
342 |
"target_language_name": "Mizo",
|
343 |
"speakers": 500000,
|
344 |
-
"bleu": 51.65580174875804
|
|
|
345 |
},
|
346 |
{
|
347 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -349,7 +392,8 @@
|
|
349 |
"target_language": "lim_Latn",
|
350 |
"target_language_name": "Limburgish",
|
351 |
"speakers": 1600000,
|
352 |
-
"bleu": 59.44855049817084
|
|
|
353 |
},
|
354 |
{
|
355 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -357,7 +401,8 @@
|
|
357 |
"target_language": "mri_Latn",
|
358 |
"target_language_name": "Maori",
|
359 |
"speakers": 160000,
|
360 |
-
"bleu": 54.831993564329125
|
|
|
361 |
},
|
362 |
{
|
363 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -365,7 +410,8 @@
|
|
365 |
"target_language": "kam_Latn",
|
366 |
"target_language_name": "Kamba",
|
367 |
"speakers": 3893000,
|
368 |
-
"bleu": 41.73348967095708
|
|
|
369 |
},
|
370 |
{
|
371 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -373,15 +419,17 @@
|
|
373 |
"target_language": "ban_Latn",
|
374 |
"target_language_name": "Bali (Indonesia)",
|
375 |
"speakers": 4000000,
|
376 |
-
"bleu": 52.87524191594727
|
|
|
377 |
},
|
378 |
{
|
379 |
"model": "anthropic/claude-3.5-sonnet",
|
380 |
"original_language": "eng_Latn",
|
381 |
"target_language": "pan_Guru",
|
382 |
-
"target_language_name": "
|
383 |
"speakers": 125000000,
|
384 |
-
"bleu": 60.
|
|
|
385 |
},
|
386 |
{
|
387 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -389,7 +437,8 @@
|
|
389 |
"target_language": "por_Latn",
|
390 |
"target_language_name": "Portuguese",
|
391 |
"speakers": 254300000,
|
392 |
-
"bleu": 77.49780742224304
|
|
|
393 |
},
|
394 |
{
|
395 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -397,7 +446,8 @@
|
|
397 |
"target_language": "crh_Latn",
|
398 |
"target_language_name": "Crimean Tatar",
|
399 |
"speakers": 552740,
|
400 |
-
"bleu": 52.705024944759934
|
|
|
401 |
},
|
402 |
{
|
403 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -405,7 +455,8 @@
|
|
405 |
"target_language": "srp_Cyrl",
|
406 |
"target_language_name": "Serbian",
|
407 |
"speakers": 9000000,
|
408 |
-
"bleu": 69.96913961762156
|
|
|
409 |
},
|
410 |
{
|
411 |
"model": "openai/gpt-4o-mini",
|
@@ -413,7 +464,8 @@
|
|
413 |
"target_language": "kas_Deva",
|
414 |
"target_language_name": "Kashmiri",
|
415 |
"speakers": 6900000,
|
416 |
-
"bleu": 22.94872648513265
|
|
|
417 |
},
|
418 |
{
|
419 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -421,7 +473,8 @@
|
|
421 |
"target_language": "kas_Deva",
|
422 |
"target_language_name": "Kashmiri",
|
423 |
"speakers": 6900000,
|
424 |
-
"bleu": 27.525562771983658
|
|
|
425 |
},
|
426 |
{
|
427 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
@@ -429,7 +482,8 @@
|
|
429 |
"target_language": "kas_Deva",
|
430 |
"target_language_name": "Kashmiri",
|
431 |
"speakers": 6900000,
|
432 |
-
"bleu": 7.999053096113321
|
|
|
433 |
},
|
434 |
{
|
435 |
"model": "mistralai/mistral-nemo",
|
@@ -437,7 +491,8 @@
|
|
437 |
"target_language": "kas_Deva",
|
438 |
"target_language_name": "Kashmiri",
|
439 |
"speakers": 6900000,
|
440 |
-
"bleu": 15.126083511737422
|
|
|
441 |
},
|
442 |
{
|
443 |
"model": "qwen/qwen-2.5-72b-instruct",
|
@@ -445,15 +500,17 @@
|
|
445 |
"target_language": "kas_Deva",
|
446 |
"target_language_name": "Kashmiri",
|
447 |
"speakers": 6900000,
|
448 |
-
"bleu": 21.928943407791756
|
|
|
449 |
},
|
450 |
{
|
451 |
"model": "anthropic/claude-3.5-sonnet",
|
452 |
"original_language": "eng_Latn",
|
453 |
"target_language": "bod_Tibt",
|
454 |
-
"target_language_name": "
|
455 |
"speakers": 1200000,
|
456 |
-
"bleu": 51.
|
|
|
457 |
},
|
458 |
{
|
459 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -461,15 +518,17 @@
|
|
461 |
"target_language": "slv_Latn",
|
462 |
"target_language_name": "Slovene",
|
463 |
"speakers": 2400000,
|
464 |
-
"bleu": 72.56912707571306
|
|
|
465 |
},
|
466 |
{
|
467 |
"model": "anthropic/claude-3.5-sonnet",
|
468 |
"original_language": "eng_Latn",
|
469 |
"target_language": "ars_Arab",
|
470 |
-
"target_language_name": "
|
471 |
"speakers": 0,
|
472 |
-
"bleu":
|
|
|
473 |
},
|
474 |
{
|
475 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -477,7 +536,8 @@
|
|
477 |
"target_language": "cat_Latn",
|
478 |
"target_language_name": "Catalan",
|
479 |
"speakers": 5100000,
|
480 |
-
"bleu": 74.45950079317922
|
|
|
481 |
},
|
482 |
{
|
483 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -485,15 +545,17 @@
|
|
485 |
"target_language": "zul_Latn",
|
486 |
"target_language_name": "Zulu",
|
487 |
"speakers": 15700000,
|
488 |
-
"bleu": 59.176207838896076
|
|
|
489 |
},
|
490 |
{
|
491 |
"model": "anthropic/claude-3.5-sonnet",
|
492 |
"original_language": "eng_Latn",
|
493 |
"target_language": "pes_Arab",
|
494 |
-
"target_language_name": "
|
495 |
"speakers": 52800000,
|
496 |
-
"bleu": 57.
|
|
|
497 |
},
|
498 |
{
|
499 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -501,7 +563,8 @@
|
|
501 |
"target_language": "taq_Latn",
|
502 |
"target_language_name": "Tamasheq",
|
503 |
"speakers": 500000,
|
504 |
-
"bleu": 25.866944911127725
|
|
|
505 |
},
|
506 |
{
|
507 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -509,7 +572,8 @@
|
|
509 |
"target_language": "snd_Deva",
|
510 |
"target_language_name": "Sindhi",
|
511 |
"speakers": 25000000,
|
512 |
-
"bleu": 40.04493401977834
|
|
|
513 |
},
|
514 |
{
|
515 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -517,7 +581,8 @@
|
|
517 |
"target_language": "ssw_Latn",
|
518 |
"target_language_name": "Swati",
|
519 |
"speakers": 2034200,
|
520 |
-
"bleu": 52.77460964391619
|
|
|
521 |
},
|
522 |
{
|
523 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -525,7 +590,8 @@
|
|
525 |
"target_language": "mkd_Cyrl",
|
526 |
"target_language_name": "Macedonian",
|
527 |
"speakers": 2000000,
|
528 |
-
"bleu": 72.27334714365769
|
|
|
529 |
},
|
530 |
{
|
531 |
"model": "openai/gpt-4o-mini",
|
@@ -533,7 +599,8 @@
|
|
533 |
"target_language": "pol_Latn",
|
534 |
"target_language_name": "Polish",
|
535 |
"speakers": 40200000,
|
536 |
-
"bleu": 63.79524354957938
|
|
|
537 |
},
|
538 |
{
|
539 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -541,7 +608,8 @@
|
|
541 |
"target_language": "pol_Latn",
|
542 |
"target_language_name": "Polish",
|
543 |
"speakers": 40200000,
|
544 |
-
"bleu": 65.97562270518736
|
|
|
545 |
},
|
546 |
{
|
547 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
@@ -549,7 +617,8 @@
|
|
549 |
"target_language": "pol_Latn",
|
550 |
"target_language_name": "Polish",
|
551 |
"speakers": 40200000,
|
552 |
-
"bleu": 62.09512880944625
|
|
|
553 |
},
|
554 |
{
|
555 |
"model": "mistralai/mistral-nemo",
|
@@ -557,7 +626,8 @@
|
|
557 |
"target_language": "pol_Latn",
|
558 |
"target_language_name": "Polish",
|
559 |
"speakers": 40200000,
|
560 |
-
"bleu": 56.42877796144466
|
|
|
561 |
},
|
562 |
{
|
563 |
"model": "qwen/qwen-2.5-72b-instruct",
|
@@ -565,7 +635,8 @@
|
|
565 |
"target_language": "pol_Latn",
|
566 |
"target_language_name": "Polish",
|
567 |
"speakers": 40200000,
|
568 |
-
"bleu": 61.08942681151859
|
|
|
569 |
},
|
570 |
{
|
571 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -573,15 +644,17 @@
|
|
573 |
"target_language": "srd_Latn",
|
574 |
"target_language_name": "Sardinian",
|
575 |
"speakers": 1300000,
|
576 |
-
"bleu": 62.69039147714039
|
|
|
577 |
},
|
578 |
{
|
579 |
"model": "anthropic/claude-3.5-sonnet",
|
580 |
"original_language": "eng_Latn",
|
581 |
"target_language": "arb_Latn",
|
582 |
-
"target_language_name": "
|
583 |
"speakers": 0,
|
584 |
-
"bleu":
|
|
|
585 |
},
|
586 |
{
|
587 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -589,7 +662,8 @@
|
|
589 |
"target_language": "twi_Latn_asan1239",
|
590 |
"target_language_name": "Twi",
|
591 |
"speakers": 3000000,
|
592 |
-
"bleu": 44.44337481309101
|
|
|
593 |
},
|
594 |
{
|
595 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -597,7 +671,8 @@
|
|
597 |
"target_language": "tum_Latn",
|
598 |
"target_language_name": "Tumbuka",
|
599 |
"speakers": 2680000,
|
600 |
-
"bleu": 44.0490017392109
|
|
|
601 |
},
|
602 |
{
|
603 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -605,7 +680,8 @@
|
|
605 |
"target_language": "fur_Latn",
|
606 |
"target_language_name": "Friulian",
|
607 |
"speakers": 300000,
|
608 |
-
"bleu": 66.54880923723718
|
|
|
609 |
},
|
610 |
{
|
611 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -613,7 +689,8 @@
|
|
613 |
"target_language": "lua_Latn",
|
614 |
"target_language_name": "Luba-Kasai",
|
615 |
"speakers": 6300000,
|
616 |
-
"bleu": 45.065529165477344
|
|
|
617 |
},
|
618 |
{
|
619 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -621,7 +698,8 @@
|
|
621 |
"target_language": "fil_Latn",
|
622 |
"target_language_name": "Filipino",
|
623 |
"speakers": 90000000,
|
624 |
-
"bleu": 70.19284983784472
|
|
|
625 |
},
|
626 |
{
|
627 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -629,7 +707,8 @@
|
|
629 |
"target_language": "afr_Latn",
|
630 |
"target_language_name": "Afrikaans",
|
631 |
"speakers": 10300000,
|
632 |
-
"bleu": 76.89005407773752
|
|
|
633 |
},
|
634 |
{
|
635 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -637,7 +716,8 @@
|
|
637 |
"target_language": "bos_Latn",
|
638 |
"target_language_name": "Bosnian",
|
639 |
"speakers": 3500000,
|
640 |
-
"bleu": 72.54880271311463
|
|
|
641 |
},
|
642 |
{
|
643 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -645,15 +725,17 @@
|
|
645 |
"target_language": "ltg_Latn",
|
646 |
"target_language_name": "Latgalian",
|
647 |
"speakers": 200000,
|
648 |
-
"bleu": 56.484355652391756
|
|
|
649 |
},
|
650 |
{
|
651 |
"model": "anthropic/claude-3.5-sonnet",
|
652 |
"original_language": "eng_Latn",
|
653 |
"target_language": "acq_Arab",
|
654 |
-
"target_language_name": "
|
655 |
"speakers": 10500000,
|
656 |
-
"bleu":
|
|
|
657 |
},
|
658 |
{
|
659 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -661,7 +743,8 @@
|
|
661 |
"target_language": "mag_Deva",
|
662 |
"target_language_name": "Magahi",
|
663 |
"speakers": 20700000,
|
664 |
-
"bleu": 58.54742215461198
|
|
|
665 |
},
|
666 |
{
|
667 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -669,7 +752,8 @@
|
|
669 |
"target_language": "min_Latn",
|
670 |
"target_language_name": "Minangkabau",
|
671 |
"speakers": 5530000,
|
672 |
-
"bleu": 64.0323403919738
|
|
|
673 |
},
|
674 |
{
|
675 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -677,15 +761,17 @@
|
|
677 |
"target_language": "kor_Hang",
|
678 |
"target_language_name": "Korean",
|
679 |
"speakers": 77300000,
|
680 |
-
"bleu": 43.68722859743311
|
|
|
681 |
},
|
682 |
{
|
683 |
"model": "anthropic/claude-3.5-sonnet",
|
684 |
"original_language": "eng_Latn",
|
685 |
"target_language": "zsm_Latn",
|
686 |
-
"target_language_name": "
|
687 |
"speakers": 0,
|
688 |
-
"bleu":
|
|
|
689 |
},
|
690 |
{
|
691 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -693,15 +779,17 @@
|
|
693 |
"target_language": "mar_Deva",
|
694 |
"target_language_name": "Marathi",
|
695 |
"speakers": 83100000,
|
696 |
-
"bleu": 57.44340907113495
|
|
|
697 |
},
|
698 |
{
|
699 |
"model": "anthropic/claude-3.5-sonnet",
|
700 |
"original_language": "eng_Latn",
|
701 |
"target_language": "pbt_Arab",
|
702 |
-
"target_language_name": "
|
703 |
"speakers": 10900000,
|
704 |
-
"bleu": 38.
|
|
|
705 |
},
|
706 |
{
|
707 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -709,15 +797,17 @@
|
|
709 |
"target_language": "lij_Latn",
|
710 |
"target_language_name": "Ligurian",
|
711 |
"speakers": 500000,
|
712 |
-
"bleu": 55.85306363017816
|
|
|
713 |
},
|
714 |
{
|
715 |
"model": "anthropic/claude-3.5-sonnet",
|
716 |
"original_language": "eng_Latn",
|
717 |
"target_language": "knc_Latn",
|
718 |
-
"target_language_name": "
|
719 |
"speakers": 0,
|
720 |
-
"bleu": 22.
|
|
|
721 |
},
|
722 |
{
|
723 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -725,7 +815,8 @@
|
|
725 |
"target_language": "chv_Cyrl",
|
726 |
"target_language_name": "Chuvash",
|
727 |
"speakers": 1279650,
|
728 |
-
"bleu": 45.05466587233098
|
|
|
729 |
},
|
730 |
{
|
731 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -733,7 +824,8 @@
|
|
733 |
"target_language": "asm_Beng",
|
734 |
"target_language_name": "Assamese",
|
735 |
"speakers": 15300000,
|
736 |
-
"bleu": 47.03513316051628
|
|
|
737 |
},
|
738 |
{
|
739 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -741,7 +833,8 @@
|
|
741 |
"target_language": "ace_Arab",
|
742 |
"target_language_name": "Aceh",
|
743 |
"speakers": 3500032,
|
744 |
-
"bleu": 23.349267705271775
|
|
|
745 |
},
|
746 |
{
|
747 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -749,7 +842,8 @@
|
|
749 |
"target_language": "tha_Thai",
|
750 |
"target_language_name": "Thai",
|
751 |
"speakers": 40000000,
|
752 |
-
"bleu": 62.81253609435389
|
|
|
753 |
},
|
754 |
{
|
755 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -757,7 +851,8 @@
|
|
757 |
"target_language": "fao_Latn",
|
758 |
"target_language_name": "Faroese",
|
759 |
"speakers": 69150,
|
760 |
-
"bleu": 65.91479024829229
|
|
|
761 |
},
|
762 |
{
|
763 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -765,7 +860,8 @@
|
|
765 |
"target_language": "nqo_Nkoo",
|
766 |
"target_language_name": "N’Ko",
|
767 |
"speakers": 0,
|
768 |
-
"bleu": 32.48349079900792
|
|
|
769 |
},
|
770 |
{
|
771 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -773,7 +869,8 @@
|
|
773 |
"target_language": "ilo_Latn",
|
774 |
"target_language_name": "Ilocano",
|
775 |
"speakers": 9100000,
|
776 |
-
"bleu": 62.605886459379576
|
|
|
777 |
},
|
778 |
{
|
779 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -781,15 +878,17 @@
|
|
781 |
"target_language": "kat_Geor",
|
782 |
"target_language_name": "Georgian",
|
783 |
"speakers": 3700000,
|
784 |
-
"bleu": 61.016636144241765
|
|
|
785 |
},
|
786 |
{
|
787 |
"model": "anthropic/claude-3.5-sonnet",
|
788 |
"original_language": "eng_Latn",
|
789 |
"target_language": "ayr_Latn",
|
790 |
-
"target_language_name": "
|
791 |
"speakers": 0,
|
792 |
-
"bleu":
|
|
|
793 |
},
|
794 |
{
|
795 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -797,7 +896,8 @@
|
|
797 |
"target_language": "dan_Latn",
|
798 |
"target_language_name": "Danish",
|
799 |
"speakers": 6000000,
|
800 |
-
"bleu": 78.0935433283814
|
|
|
801 |
},
|
802 |
{
|
803 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -805,7 +905,8 @@
|
|
805 |
"target_language": "brx_Deva",
|
806 |
"target_language_name": "Boro (India)",
|
807 |
"speakers": 1482929,
|
808 |
-
"bleu": 36.11004749691388
|
|
|
809 |
},
|
810 |
{
|
811 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -813,15 +914,17 @@
|
|
813 |
"target_language": "sag_Latn",
|
814 |
"target_language_name": "Sango",
|
815 |
"speakers": 4600000,
|
816 |
-
"bleu": 34.875422265717596
|
|
|
817 |
},
|
818 |
{
|
819 |
"model": "anthropic/claude-3.5-sonnet",
|
820 |
"original_language": "eng_Latn",
|
821 |
"target_language": "lvs_Latn",
|
822 |
-
"target_language_name": "
|
823 |
"speakers": 0,
|
824 |
-
"bleu":
|
|
|
825 |
},
|
826 |
{
|
827 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -829,7 +932,8 @@
|
|
829 |
"target_language": "jpn_Jpan",
|
830 |
"target_language_name": "Japanese",
|
831 |
"speakers": 128000000,
|
832 |
-
"bleu": 49.91661356931259
|
|
|
833 |
},
|
834 |
{
|
835 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -837,7 +941,8 @@
|
|
837 |
"target_language": "uig_Arab",
|
838 |
"target_language_name": "Uyghur",
|
839 |
"speakers": 10400000,
|
840 |
-
"bleu": 53.53468771030665
|
|
|
841 |
},
|
842 |
{
|
843 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -845,7 +950,8 @@
|
|
845 |
"target_language": "fra_Latn",
|
846 |
"target_language_name": "French",
|
847 |
"speakers": 208157220,
|
848 |
-
"bleu": 79.3023871219446
|
|
|
849 |
},
|
850 |
{
|
851 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -853,7 +959,8 @@
|
|
853 |
"target_language": "jav_Latn",
|
854 |
"target_language_name": "Javanese",
|
855 |
"speakers": 84308740,
|
856 |
-
"bleu": 60.44033529900538
|
|
|
857 |
},
|
858 |
{
|
859 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -861,7 +968,8 @@
|
|
861 |
"target_language": "sun_Latn",
|
862 |
"target_language_name": "Sunda",
|
863 |
"speakers": 32400000,
|
864 |
-
"bleu": 56.40659991041485
|
|
|
865 |
},
|
866 |
{
|
867 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -869,7 +977,8 @@
|
|
869 |
"target_language": "umb_Latn",
|
870 |
"target_language_name": "Umbundu",
|
871 |
"speakers": 6000000,
|
872 |
-
"bleu": 21.080277559665817
|
|
|
873 |
},
|
874 |
{
|
875 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -877,7 +986,8 @@
|
|
877 |
"target_language": "bel_Cyrl",
|
878 |
"target_language_name": "Belarusian",
|
879 |
"speakers": 7900000,
|
880 |
-
"bleu": 54.51951664423131
|
|
|
881 |
},
|
882 |
{
|
883 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -885,15 +995,17 @@
|
|
885 |
"target_language": "cjk_Latn",
|
886 |
"target_language_name": "Chokwe",
|
887 |
"speakers": 0,
|
888 |
-
"bleu": 10.186407416077753
|
|
|
889 |
},
|
890 |
{
|
891 |
"model": "anthropic/claude-3.5-sonnet",
|
892 |
"original_language": "eng_Latn",
|
893 |
"target_language": "yue_Hant",
|
894 |
-
"target_language_name": "
|
895 |
"speakers": 73100000,
|
896 |
-
"bleu": 34.
|
|
|
897 |
},
|
898 |
{
|
899 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -901,15 +1013,17 @@
|
|
901 |
"target_language": "hat_Latn",
|
902 |
"target_language_name": "Haitian Creole",
|
903 |
"speakers": 9600000,
|
904 |
-
"bleu": 63.85321875910916
|
|
|
905 |
},
|
906 |
{
|
907 |
"model": "anthropic/claude-3.5-sonnet",
|
908 |
"original_language": "eng_Latn",
|
909 |
"target_language": "kmr_Latn",
|
910 |
-
"target_language_name": "
|
911 |
"speakers": 14600000,
|
912 |
-
"bleu": 55.
|
|
|
913 |
},
|
914 |
{
|
915 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -917,7 +1031,8 @@
|
|
917 |
"target_language": "ceb_Latn",
|
918 |
"target_language_name": "Cebuano",
|
919 |
"speakers": 15900000,
|
920 |
-
"bleu": 69.455795865483
|
|
|
921 |
},
|
922 |
{
|
923 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -925,15 +1040,17 @@
|
|
925 |
"target_language": "dzo_Tibt",
|
926 |
"target_language_name": "Dzongkha",
|
927 |
"speakers": 237080,
|
928 |
-
"bleu": 44.35738140173861
|
|
|
929 |
},
|
930 |
{
|
931 |
"model": "anthropic/claude-3.5-sonnet",
|
932 |
"original_language": "eng_Latn",
|
933 |
"target_language": "deu_Latn",
|
934 |
-
"target_language_name": "
|
935 |
"speakers": 105000000,
|
936 |
-
"bleu": 77.
|
|
|
937 |
},
|
938 |
{
|
939 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -941,7 +1058,8 @@
|
|
941 |
"target_language": "ibo_Latn",
|
942 |
"target_language_name": "Igbo",
|
943 |
"speakers": 27000000,
|
944 |
-
"bleu": 46.40173449341075
|
|
|
945 |
},
|
946 |
{
|
947 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -949,23 +1067,26 @@
|
|
949 |
"target_language": "vie_Latn",
|
950 |
"target_language_name": "Vietnamese",
|
951 |
"speakers": 76000000,
|
952 |
-
"bleu": 70.35607494641172
|
|
|
953 |
},
|
954 |
{
|
955 |
"model": "anthropic/claude-3.5-sonnet",
|
956 |
"original_language": "eng_Latn",
|
957 |
"target_language": "quy_Latn",
|
958 |
-
"target_language_name": "
|
959 |
"speakers": 918200,
|
960 |
-
"bleu":
|
|
|
961 |
},
|
962 |
{
|
963 |
"model": "anthropic/claude-3.5-sonnet",
|
964 |
"original_language": "eng_Latn",
|
965 |
"target_language": "cmn_Hant",
|
966 |
-
"target_language_name": "
|
967 |
"speakers": 1074000000,
|
968 |
-
"bleu": 41.
|
|
|
969 |
},
|
970 |
{
|
971 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -973,7 +1094,8 @@
|
|
973 |
"target_language": "mai_Deva",
|
974 |
"target_language_name": "Maithili",
|
975 |
"speakers": 33900000,
|
976 |
-
"bleu": 54.65300713908629
|
|
|
977 |
},
|
978 |
{
|
979 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -981,7 +1103,8 @@
|
|
981 |
"target_language": "gla_Latn",
|
982 |
"target_language_name": "Scottish Gaelic",
|
983 |
"speakers": 60130,
|
984 |
-
"bleu": 62.604437133773324
|
|
|
985 |
},
|
986 |
{
|
987 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -989,7 +1112,8 @@
|
|
989 |
"target_language": "urd_Arab",
|
990 |
"target_language_name": "Urdu",
|
991 |
"speakers": 94022900,
|
992 |
-
"bleu": 61.12554572717868
|
|
|
993 |
},
|
994 |
{
|
995 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -997,7 +1121,8 @@
|
|
997 |
"target_language": "shn_Mymr",
|
998 |
"target_language_name": "Shan",
|
999 |
"speakers": 3000000,
|
1000 |
-
"bleu": 29.21299485766884
|
|
|
1001 |
},
|
1002 |
{
|
1003 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1005,15 +1130,17 @@
|
|
1005 |
"target_language": "wol_Latn",
|
1006 |
"target_language_name": "Wolof",
|
1007 |
"speakers": 3700000,
|
1008 |
-
"bleu": 42.64301275691043
|
|
|
1009 |
},
|
1010 |
{
|
1011 |
"model": "anthropic/claude-3.5-sonnet",
|
1012 |
"original_language": "eng_Latn",
|
1013 |
"target_language": "cmn_Hans",
|
1014 |
-
"target_language_name": "
|
1015 |
"speakers": 1074000000,
|
1016 |
-
"bleu": 43.
|
|
|
1017 |
},
|
1018 |
{
|
1019 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1021,15 +1148,17 @@
|
|
1021 |
"target_language": "guj_Gujr",
|
1022 |
"target_language_name": "Gujarati",
|
1023 |
"speakers": 56400000,
|
1024 |
-
"bleu": 55.588451345198735
|
|
|
1025 |
},
|
1026 |
{
|
1027 |
"model": "anthropic/claude-3.5-sonnet",
|
1028 |
"original_language": "eng_Latn",
|
1029 |
"target_language": "ekk_Latn",
|
1030 |
-
"target_language_name": "
|
1031 |
"speakers": 1164770,
|
1032 |
-
"bleu":
|
|
|
1033 |
},
|
1034 |
{
|
1035 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1037,7 +1166,8 @@
|
|
1037 |
"target_language": "luo_Latn",
|
1038 |
"target_language_name": "Dholuo",
|
1039 |
"speakers": 3000000,
|
1040 |
-
"bleu": 46.41194790710186
|
|
|
1041 |
},
|
1042 |
{
|
1043 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1045,15 +1175,17 @@
|
|
1045 |
"target_language": "hrv_Latn",
|
1046 |
"target_language_name": "Croatian",
|
1047 |
"speakers": 7000000,
|
1048 |
-
"bleu": 69.54569836615161
|
|
|
1049 |
},
|
1050 |
{
|
1051 |
"model": "anthropic/claude-3.5-sonnet",
|
1052 |
"original_language": "eng_Latn",
|
1053 |
"target_language": "uzn_Latn",
|
1054 |
-
"target_language_name": "
|
1055 |
"speakers": 26912410,
|
1056 |
-
"bleu":
|
|
|
1057 |
},
|
1058 |
{
|
1059 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1061,7 +1193,8 @@
|
|
1061 |
"target_language": "ben_Beng",
|
1062 |
"target_language_name": "Bengali",
|
1063 |
"speakers": 300000000,
|
1064 |
-
"bleu": 57.14175888160181
|
|
|
1065 |
},
|
1066 |
{
|
1067 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1069,7 +1202,8 @@
|
|
1069 |
"target_language": "nya_Latn",
|
1070 |
"target_language_name": "Chichewa",
|
1071 |
"speakers": 12000000,
|
1072 |
-
"bleu": 59.76016801606614
|
|
|
1073 |
},
|
1074 |
{
|
1075 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1077,7 +1211,8 @@
|
|
1077 |
"target_language": "tsn_Latn",
|
1078 |
"target_language_name": "Setswana",
|
1079 |
"speakers": 4500000,
|
1080 |
-
"bleu": 55.22888902281337
|
|
|
1081 |
},
|
1082 |
{
|
1083 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1085,15 +1220,17 @@
|
|
1085 |
"target_language": "fin_Latn",
|
1086 |
"target_language_name": "Finnish",
|
1087 |
"speakers": 5413380,
|
1088 |
-
"bleu": 70.94250295175219
|
|
|
1089 |
},
|
1090 |
{
|
1091 |
"model": "anthropic/claude-3.5-sonnet",
|
1092 |
"original_language": "eng_Latn",
|
1093 |
"target_language": "nso_Latn",
|
1094 |
-
"target_language_name": "
|
1095 |
"speakers": 4100000,
|
1096 |
-
"bleu":
|
|
|
1097 |
},
|
1098 |
{
|
1099 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1101,7 +1238,8 @@
|
|
1101 |
"target_language": "sna_Latn",
|
1102 |
"target_language_name": "Shona",
|
1103 |
"speakers": 9023000,
|
1104 |
-
"bleu": 51.55921914049446
|
|
|
1105 |
},
|
1106 |
{
|
1107 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1109,7 +1247,8 @@
|
|
1109 |
"target_language": "snd_Arab",
|
1110 |
"target_language_name": "Sindhi",
|
1111 |
"speakers": 25000000,
|
1112 |
-
"bleu": 56.33027730975489
|
|
|
1113 |
},
|
1114 |
{
|
1115 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1117,7 +1256,8 @@
|
|
1117 |
"target_language": "xho_Latn",
|
1118 |
"target_language_name": "Xhosa",
|
1119 |
"speakers": 11000000,
|
1120 |
-
"bleu": 55.46880910094653
|
|
|
1121 |
},
|
1122 |
{
|
1123 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1125,7 +1265,8 @@
|
|
1125 |
"target_language": "kik_Latn",
|
1126 |
"target_language_name": "Gikuyu",
|
1127 |
"speakers": 6623000,
|
1128 |
-
"bleu": 40.92882752909001
|
|
|
1129 |
},
|
1130 |
{
|
1131 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1133,7 +1274,8 @@
|
|
1133 |
"target_language": "tso_Latn",
|
1134 |
"target_language_name": "Tsonga",
|
1135 |
"speakers": 13000000,
|
1136 |
-
"bleu": 58.35165735971044
|
|
|
1137 |
},
|
1138 |
{
|
1139 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1141,7 +1283,8 @@
|
|
1141 |
"target_language": "tat_Cyrl",
|
1142 |
"target_language_name": "Tatar",
|
1143 |
"speakers": 5427318,
|
1144 |
-
"bleu": 60.3447467212788
|
|
|
1145 |
},
|
1146 |
{
|
1147 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1149,15 +1292,17 @@
|
|
1149 |
"target_language": "awa_Deva",
|
1150 |
"target_language_name": "Awadhi",
|
1151 |
"speakers": 22000000,
|
1152 |
-
"bleu": 46.0797144146192
|
|
|
1153 |
},
|
1154 |
{
|
1155 |
"model": "anthropic/claude-3.5-sonnet",
|
1156 |
"original_language": "eng_Latn",
|
1157 |
"target_language": "gom_Deva",
|
1158 |
-
"target_language_name": "
|
1159 |
"speakers": 3633900,
|
1160 |
-
"bleu":
|
|
|
1161 |
},
|
1162 |
{
|
1163 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1165,7 +1310,8 @@
|
|
1165 |
"target_language": "amh_Ethi",
|
1166 |
"target_language_name": "Amharic",
|
1167 |
"speakers": 25000000,
|
1168 |
-
"bleu": 43.15445686971015
|
|
|
1169 |
},
|
1170 |
{
|
1171 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1173,7 +1319,8 @@
|
|
1173 |
"target_language": "tam_Taml",
|
1174 |
"target_language_name": "Tamil",
|
1175 |
"speakers": 75000000,
|
1176 |
-
"bleu": 65.78632210538115
|
|
|
1177 |
},
|
1178 |
{
|
1179 |
"model": "openai/gpt-4o-mini",
|
@@ -1181,7 +1328,8 @@
|
|
1181 |
"target_language": "isl_Latn",
|
1182 |
"target_language_name": "Icelandic",
|
1183 |
"speakers": 358000,
|
1184 |
-
"bleu": 61.13552606922321
|
|
|
1185 |
},
|
1186 |
{
|
1187 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1189,7 +1337,8 @@
|
|
1189 |
"target_language": "isl_Latn",
|
1190 |
"target_language_name": "Icelandic",
|
1191 |
"speakers": 358000,
|
1192 |
-
"bleu": 66.67473000551618
|
|
|
1193 |
},
|
1194 |
{
|
1195 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
@@ -1197,7 +1346,8 @@
|
|
1197 |
"target_language": "isl_Latn",
|
1198 |
"target_language_name": "Icelandic",
|
1199 |
"speakers": 358000,
|
1200 |
-
"bleu": 58.60923195347865
|
|
|
1201 |
},
|
1202 |
{
|
1203 |
"model": "mistralai/mistral-nemo",
|
@@ -1205,7 +1355,8 @@
|
|
1205 |
"target_language": "isl_Latn",
|
1206 |
"target_language_name": "Icelandic",
|
1207 |
"speakers": 358000,
|
1208 |
-
"bleu": 45.58482442810681
|
|
|
1209 |
},
|
1210 |
{
|
1211 |
"model": "qwen/qwen-2.5-72b-instruct",
|
@@ -1213,7 +1364,8 @@
|
|
1213 |
"target_language": "isl_Latn",
|
1214 |
"target_language_name": "Icelandic",
|
1215 |
"speakers": 358000,
|
1216 |
-
"bleu": 40.16071522003955
|
|
|
1217 |
},
|
1218 |
{
|
1219 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1221,15 +1373,17 @@
|
|
1221 |
"target_language": "san_Deva",
|
1222 |
"target_language_name": "Sanskrit",
|
1223 |
"speakers": 49736,
|
1224 |
-
"bleu": 32.78132499113236
|
|
|
1225 |
},
|
1226 |
{
|
1227 |
"model": "anthropic/claude-3.5-sonnet",
|
1228 |
"original_language": "eng_Latn",
|
1229 |
"target_language": "als_Latn",
|
1230 |
-
"target_language_name": "
|
1231 |
"speakers": 3000000,
|
1232 |
-
"bleu": 69.
|
|
|
1233 |
},
|
1234 |
{
|
1235 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1237,7 +1391,8 @@
|
|
1237 |
"target_language": "ron_Latn",
|
1238 |
"target_language_name": "Romanian",
|
1239 |
"speakers": 24300000,
|
1240 |
-
"bleu": 76.4907159034647
|
|
|
1241 |
},
|
1242 |
{
|
1243 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1245,7 +1400,8 @@
|
|
1245 |
"target_language": "kaz_Cyrl",
|
1246 |
"target_language_name": "Kazakh",
|
1247 |
"speakers": 13161980,
|
1248 |
-
"bleu": 61.12516213751114
|
|
|
1249 |
},
|
1250 |
{
|
1251 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1253,7 +1409,8 @@
|
|
1253 |
"target_language": "sat_Olck",
|
1254 |
"target_language_name": "Santhali",
|
1255 |
"speakers": 7200000,
|
1256 |
-
"bleu": 31.51192472690372
|
|
|
1257 |
},
|
1258 |
{
|
1259 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1261,15 +1418,17 @@
|
|
1261 |
"target_language": "ukr_Cyrl",
|
1262 |
"target_language_name": "Ukrainian",
|
1263 |
"speakers": 34710100,
|
1264 |
-
"bleu": 68.09762325436868
|
|
|
1265 |
},
|
1266 |
{
|
1267 |
"model": "anthropic/claude-3.5-sonnet",
|
1268 |
"original_language": "eng_Latn",
|
1269 |
"target_language": "khk_Cyrl",
|
1270 |
-
"target_language_name": "
|
1271 |
"speakers": 2704030,
|
1272 |
-
"bleu":
|
|
|
1273 |
},
|
1274 |
{
|
1275 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1277,7 +1436,8 @@
|
|
1277 |
"target_language": "bjn_Latn",
|
1278 |
"target_language_name": "Banjar",
|
1279 |
"speakers": 3500000,
|
1280 |
-
"bleu": 56.309519555010915
|
|
|
1281 |
},
|
1282 |
{
|
1283 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1285,7 +1445,8 @@
|
|
1285 |
"target_language": "fon_Latn",
|
1286 |
"target_language_name": "Fon",
|
1287 |
"speakers": 1935500,
|
1288 |
-
"bleu": 25.279777366609945
|
|
|
1289 |
},
|
1290 |
{
|
1291 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1293,7 +1454,8 @@
|
|
1293 |
"target_language": "sin_Sinh",
|
1294 |
"target_language_name": "Sinhala",
|
1295 |
"speakers": 15300000,
|
1296 |
-
"bleu": 56.75673117959971
|
|
|
1297 |
},
|
1298 |
{
|
1299 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1301,7 +1463,8 @@
|
|
1301 |
"target_language": "nno_Latn",
|
1302 |
"target_language_name": "nno",
|
1303 |
"speakers": 0,
|
1304 |
-
"bleu": 71.86156462958435
|
|
|
1305 |
},
|
1306 |
{
|
1307 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1309,7 +1472,8 @@
|
|
1309 |
"target_language": "hau_Latn",
|
1310 |
"target_language_name": "Hausa",
|
1311 |
"speakers": 43900000,
|
1312 |
-
"bleu": 56.34319579006431
|
|
|
1313 |
},
|
1314 |
{
|
1315 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1317,7 +1481,8 @@
|
|
1317 |
"target_language": "prs_Arab",
|
1318 |
"target_language_name": "Dari",
|
1319 |
"speakers": 9600000,
|
1320 |
-
"bleu": 52.55397957953147
|
|
|
1321 |
},
|
1322 |
{
|
1323 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1325,7 +1490,8 @@
|
|
1325 |
"target_language": "ell_Grek",
|
1326 |
"target_language_name": "Greek",
|
1327 |
"speakers": 15000000,
|
1328 |
-
"bleu": 66.23477821529342
|
|
|
1329 |
},
|
1330 |
{
|
1331 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1333,7 +1499,8 @@
|
|
1333 |
"target_language": "tpi_Latn",
|
1334 |
"target_language_name": "Tok Pisin",
|
1335 |
"speakers": 4000000,
|
1336 |
-
"bleu": 56.54077603673191
|
|
|
1337 |
},
|
1338 |
{
|
1339 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1341,7 +1508,8 @@
|
|
1341 |
"target_language": "hye_Armn",
|
1342 |
"target_language_name": "Armenian",
|
1343 |
"speakers": 6700000,
|
1344 |
-
"bleu": 64.68044008058686
|
|
|
1345 |
},
|
1346 |
{
|
1347 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1349,7 +1517,8 @@
|
|
1349 |
"target_language": "eus_Latn",
|
1350 |
"target_language_name": "Basque",
|
1351 |
"speakers": 750000,
|
1352 |
-
"bleu": 65.89687213771296
|
|
|
1353 |
},
|
1354 |
{
|
1355 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1357,7 +1526,8 @@
|
|
1357 |
"target_language": "nob_Latn",
|
1358 |
"target_language_name": "Bokmål",
|
1359 |
"speakers": 4000000,
|
1360 |
-
"bleu": 77.49395130155645
|
|
|
1361 |
},
|
1362 |
{
|
1363 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1365,15 +1535,17 @@
|
|
1365 |
"target_language": "slk_Latn",
|
1366 |
"target_language_name": "Slovak",
|
1367 |
"speakers": 6000000,
|
1368 |
-
"bleu": 67.92848040860814
|
|
|
1369 |
},
|
1370 |
{
|
1371 |
"model": "anthropic/claude-3.5-sonnet",
|
1372 |
"original_language": "eng_Latn",
|
1373 |
"target_language": "knc_Arab",
|
1374 |
-
"target_language_name": "
|
1375 |
"speakers": 0,
|
1376 |
-
"bleu": 14.
|
|
|
1377 |
},
|
1378 |
{
|
1379 |
"model": "openai/gpt-4o-mini",
|
@@ -1381,7 +1553,8 @@
|
|
1381 |
"target_language": "lin_Latn",
|
1382 |
"target_language_name": "Lingala",
|
1383 |
"speakers": 20000000,
|
1384 |
-
"bleu": 50.384710146677506
|
|
|
1385 |
},
|
1386 |
{
|
1387 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1389,7 +1562,8 @@
|
|
1389 |
"target_language": "lin_Latn",
|
1390 |
"target_language_name": "Lingala",
|
1391 |
"speakers": 20000000,
|
1392 |
-
"bleu": 56.735518064625495
|
|
|
1393 |
},
|
1394 |
{
|
1395 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
@@ -1397,7 +1571,8 @@
|
|
1397 |
"target_language": "lin_Latn",
|
1398 |
"target_language_name": "Lingala",
|
1399 |
"speakers": 20000000,
|
1400 |
-
"bleu": 19.732953348932526
|
|
|
1401 |
},
|
1402 |
{
|
1403 |
"model": "mistralai/mistral-nemo",
|
@@ -1405,7 +1580,8 @@
|
|
1405 |
"target_language": "lin_Latn",
|
1406 |
"target_language_name": "Lingala",
|
1407 |
"speakers": 20000000,
|
1408 |
-
"bleu": 8.64985622273109
|
|
|
1409 |
},
|
1410 |
{
|
1411 |
"model": "qwen/qwen-2.5-72b-instruct",
|
@@ -1413,7 +1589,8 @@
|
|
1413 |
"target_language": "lin_Latn",
|
1414 |
"target_language_name": "Lingala",
|
1415 |
"speakers": 20000000,
|
1416 |
-
"bleu": 16.658410482633357
|
|
|
1417 |
},
|
1418 |
{
|
1419 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1421,15 +1598,17 @@
|
|
1421 |
"target_language": "bam_Latn",
|
1422 |
"target_language_name": "Bamanankan",
|
1423 |
"speakers": 2700000,
|
1424 |
-
"bleu": 38.693909140769804
|
|
|
1425 |
},
|
1426 |
{
|
1427 |
"model": "anthropic/claude-3.5-sonnet",
|
1428 |
"original_language": "eng_Latn",
|
1429 |
"target_language": "sot_Latn",
|
1430 |
-
"target_language_name": "
|
1431 |
"speakers": 6000000,
|
1432 |
-
"bleu":
|
|
|
1433 |
},
|
1434 |
{
|
1435 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1437,23 +1616,26 @@
|
|
1437 |
"target_language": "min_Arab",
|
1438 |
"target_language_name": "Minangkabau",
|
1439 |
"speakers": 5530000,
|
1440 |
-
"bleu": 37.44925084737469
|
|
|
1441 |
},
|
1442 |
{
|
1443 |
"model": "anthropic/claude-3.5-sonnet",
|
1444 |
"original_language": "eng_Latn",
|
1445 |
"target_language": "zgh_Tfng",
|
1446 |
-
"target_language_name": "
|
1447 |
"speakers": 0,
|
1448 |
-
"bleu":
|
|
|
1449 |
},
|
1450 |
{
|
1451 |
"model": "anthropic/claude-3.5-sonnet",
|
1452 |
"original_language": "eng_Latn",
|
1453 |
"target_language": "gug_Latn",
|
1454 |
-
"target_language_name": "
|
1455 |
"speakers": 0,
|
1456 |
-
"bleu":
|
|
|
1457 |
},
|
1458 |
{
|
1459 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1461,7 +1643,8 @@
|
|
1461 |
"target_language": "lmo_Latn",
|
1462 |
"target_language_name": "Lombard",
|
1463 |
"speakers": 3900000,
|
1464 |
-
"bleu": 46.38844026736926
|
|
|
1465 |
},
|
1466 |
{
|
1467 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1469,7 +1652,8 @@
|
|
1469 |
"target_language": "yor_Latn",
|
1470 |
"target_language_name": "Yoruba",
|
1471 |
"speakers": 40000000,
|
1472 |
-
"bleu": 34.264254226792296
|
|
|
1473 |
},
|
1474 |
{
|
1475 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1477,7 +1661,8 @@
|
|
1477 |
"target_language": "taq_Tfng",
|
1478 |
"target_language_name": "Tamasheq",
|
1479 |
"speakers": 500000,
|
1480 |
-
"bleu": 10.997033033155907
|
|
|
1481 |
},
|
1482 |
{
|
1483 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1485,15 +1670,17 @@
|
|
1485 |
"target_language": "tgk_Cyrl",
|
1486 |
"target_language_name": "Tajik",
|
1487 |
"speakers": 14000000,
|
1488 |
-
"bleu": 60.97836841576954
|
|
|
1489 |
},
|
1490 |
{
|
1491 |
"model": "anthropic/claude-3.5-sonnet",
|
1492 |
"original_language": "eng_Latn",
|
1493 |
"target_language": "fuv_Latn",
|
1494 |
-
"target_language_name": "
|
1495 |
"speakers": 14500000,
|
1496 |
-
"bleu": 28.
|
|
|
1497 |
},
|
1498 |
{
|
1499 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1501,7 +1688,8 @@
|
|
1501 |
"target_language": "mal_Mlym",
|
1502 |
"target_language_name": "Malayalam",
|
1503 |
"speakers": 37100000,
|
1504 |
-
"bleu": 64.06558940908465
|
|
|
1505 |
},
|
1506 |
{
|
1507 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1509,15 +1697,17 @@
|
|
1509 |
"target_language": "tel_Telu",
|
1510 |
"target_language_name": "Telugu",
|
1511 |
"speakers": 82000000,
|
1512 |
-
"bleu": 61.635245762892694
|
|
|
1513 |
},
|
1514 |
{
|
1515 |
"model": "anthropic/claude-3.5-sonnet",
|
1516 |
"original_language": "eng_Latn",
|
1517 |
"target_language": "arb_Arab",
|
1518 |
-
"target_language_name": "
|
1519 |
"speakers": 0,
|
1520 |
-
"bleu": 65.
|
|
|
1521 |
},
|
1522 |
{
|
1523 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1525,7 +1715,8 @@
|
|
1525 |
"target_language": "khm_Khmr",
|
1526 |
"target_language_name": "Khmer",
|
1527 |
"speakers": 16600000,
|
1528 |
-
"bleu": 49.209825704340375
|
|
|
1529 |
},
|
1530 |
{
|
1531 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1533,7 +1724,8 @@
|
|
1533 |
"target_language": "scn_Latn",
|
1534 |
"target_language_name": "Sicilian",
|
1535 |
"speakers": 4700000,
|
1536 |
-
"bleu": 58.589535944250635
|
|
|
1537 |
},
|
1538 |
{
|
1539 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1541,7 +1733,8 @@
|
|
1541 |
"target_language": "ltz_Latn",
|
1542 |
"target_language_name": "Luxembourgish",
|
1543 |
"speakers": 391200,
|
1544 |
-
"bleu": 70.8338190437548
|
|
|
1545 |
},
|
1546 |
{
|
1547 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1549,7 +1742,8 @@
|
|
1549 |
"target_language": "pag_Latn",
|
1550 |
"target_language_name": "Pangasinan",
|
1551 |
"speakers": 1100000,
|
1552 |
-
"bleu": 56.00481838266269
|
|
|
1553 |
},
|
1554 |
{
|
1555 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1557,7 +1751,8 @@
|
|
1557 |
"target_language": "kab_Latn",
|
1558 |
"target_language_name": "Kabyle",
|
1559 |
"speakers": 5586000,
|
1560 |
-
"bleu": 41.14429925869902
|
|
|
1561 |
},
|
1562 |
{
|
1563 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1565,7 +1760,8 @@
|
|
1565 |
"target_language": "bak_Cyrl",
|
1566 |
"target_language_name": "Bashkort",
|
1567 |
"speakers": 1200000,
|
1568 |
-
"bleu": 57.54538429274717
|
|
|
1569 |
},
|
1570 |
{
|
1571 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1573,7 +1769,8 @@
|
|
1573 |
"target_language": "twi_Latn_akua1239",
|
1574 |
"target_language_name": "Twi",
|
1575 |
"speakers": 3000000,
|
1576 |
-
"bleu": 45.1519376004116
|
|
|
1577 |
},
|
1578 |
{
|
1579 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1581,7 +1778,8 @@
|
|
1581 |
"target_language": "hin_Deva",
|
1582 |
"target_language_name": "Hindi",
|
1583 |
"speakers": 341000000,
|
1584 |
-
"bleu": 64.936216689785
|
|
|
1585 |
},
|
1586 |
{
|
1587 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1589,7 +1787,8 @@
|
|
1589 |
"target_language": "kas_Arab",
|
1590 |
"target_language_name": "Kashmiri",
|
1591 |
"speakers": 6900000,
|
1592 |
-
"bleu": 38.28328065553461
|
|
|
1593 |
},
|
1594 |
{
|
1595 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1597,7 +1796,8 @@
|
|
1597 |
"target_language": "mlt_Latn",
|
1598 |
"target_language_name": "Maltese",
|
1599 |
"speakers": 570000,
|
1600 |
-
"bleu": 80.08667772627608
|
|
|
1601 |
},
|
1602 |
{
|
1603 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1605,7 +1805,8 @@
|
|
1605 |
"target_language": "som_Latn",
|
1606 |
"target_language_name": "Somali",
|
1607 |
"speakers": 16200000,
|
1608 |
-
"bleu": 55.370649647294535
|
|
|
1609 |
},
|
1610 |
{
|
1611 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1613,7 +1814,8 @@
|
|
1613 |
"target_language": "hne_Deva",
|
1614 |
"target_language_name": "Chhattisgarhi",
|
1615 |
"speakers": 16300000,
|
1616 |
-
"bleu": 47.979750130407254
|
|
|
1617 |
},
|
1618 |
{
|
1619 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1621,7 +1823,8 @@
|
|
1621 |
"target_language": "glg_Latn",
|
1622 |
"target_language_name": "Galician",
|
1623 |
"speakers": 2500000,
|
1624 |
-
"bleu": 68.70247869041181
|
|
|
1625 |
},
|
1626 |
{
|
1627 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1629,7 +1832,8 @@
|
|
1629 |
"target_language": "ory_Orya",
|
1630 |
"target_language_name": "Odia",
|
1631 |
"speakers": 34500000,
|
1632 |
-
"bleu": 57.362809651798656
|
|
|
1633 |
},
|
1634 |
{
|
1635 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1637,15 +1841,17 @@
|
|
1637 |
"target_language": "nld_Latn",
|
1638 |
"target_language_name": "Dutch",
|
1639 |
"speakers": 23100000,
|
1640 |
-
"bleu": 71.18493263152928
|
|
|
1641 |
},
|
1642 |
{
|
1643 |
"model": "anthropic/claude-3.5-sonnet",
|
1644 |
"original_language": "eng_Latn",
|
1645 |
"target_language": "apc_Arab_sout3123",
|
1646 |
-
"target_language_name": "
|
1647 |
"speakers": 44000000,
|
1648 |
-
"bleu":
|
|
|
1649 |
},
|
1650 |
{
|
1651 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1653,7 +1859,8 @@
|
|
1653 |
"target_language": "oci_Latn",
|
1654 |
"target_language_name": "Occitan",
|
1655 |
"speakers": 542000,
|
1656 |
-
"bleu": 71.53274018395614
|
|
|
1657 |
},
|
1658 |
{
|
1659 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1661,7 +1868,8 @@
|
|
1661 |
"target_language": "mni_Beng",
|
1662 |
"target_language_name": "Meitei",
|
1663 |
"speakers": 1470000,
|
1664 |
-
"bleu": 40.61648039338993
|
|
|
1665 |
},
|
1666 |
{
|
1667 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1669,7 +1877,8 @@
|
|
1669 |
"target_language": "hun_Latn",
|
1670 |
"target_language_name": "Hungarian",
|
1671 |
"speakers": 12600000,
|
1672 |
-
"bleu": 66.13011194084116
|
|
|
1673 |
},
|
1674 |
{
|
1675 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1677,7 +1886,8 @@
|
|
1677 |
"target_language": "bho_Deva",
|
1678 |
"target_language_name": "Bhojpuri",
|
1679 |
"speakers": 52200000,
|
1680 |
-
"bleu": 44.54123379070156
|
|
|
1681 |
},
|
1682 |
{
|
1683 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1685,7 +1895,8 @@
|
|
1685 |
"target_language": "mya_Mymr",
|
1686 |
"target_language_name": "Burmese",
|
1687 |
"speakers": 32900000,
|
1688 |
-
"bleu": 55.723591167735165
|
|
|
1689 |
},
|
1690 |
{
|
1691 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1693,7 +1904,8 @@
|
|
1693 |
"target_language": "run_Latn",
|
1694 |
"target_language_name": "Rundi",
|
1695 |
"speakers": 10800000,
|
1696 |
-
"bleu": 48.94351362900039
|
|
|
1697 |
},
|
1698 |
{
|
1699 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1701,7 +1913,8 @@
|
|
1701 |
"target_language": "ast_Latn",
|
1702 |
"target_language_name": "Asturian",
|
1703 |
"speakers": 450000,
|
1704 |
-
"bleu": 71.34456234933488
|
|
|
1705 |
},
|
1706 |
{
|
1707 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1709,7 +1922,8 @@
|
|
1709 |
"target_language": "tir_Ethi",
|
1710 |
"target_language_name": "Tigrigna",
|
1711 |
"speakers": 7507780,
|
1712 |
-
"bleu": 32.87119617033141
|
|
|
1713 |
},
|
1714 |
{
|
1715 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1717,31 +1931,35 @@
|
|
1717 |
"target_language": "kac_Latn",
|
1718 |
"target_language_name": "Jingpho",
|
1719 |
"speakers": 940000,
|
1720 |
-
"bleu": 43.550058140290794
|
|
|
1721 |
},
|
1722 |
{
|
1723 |
"model": "anthropic/claude-3.5-sonnet",
|
1724 |
"original_language": "eng_Latn",
|
1725 |
"target_language": "acm_Arab",
|
1726 |
-
"target_language_name": "
|
1727 |
"speakers": 15700000,
|
1728 |
-
"bleu":
|
|
|
1729 |
},
|
1730 |
{
|
1731 |
"model": "anthropic/claude-3.5-sonnet",
|
1732 |
"original_language": "eng_Latn",
|
1733 |
"target_language": "arz_Arab",
|
1734 |
-
"target_language_name": "
|
1735 |
"speakers": 100542400,
|
1736 |
-
"bleu":
|
|
|
1737 |
},
|
1738 |
{
|
1739 |
"model": "anthropic/claude-3.5-sonnet",
|
1740 |
"original_language": "eng_Latn",
|
1741 |
"target_language": "mhr_Cyrl",
|
1742 |
-
"target_language_name": "
|
1743 |
"speakers": 482000,
|
1744 |
-
"bleu": 49.
|
|
|
1745 |
},
|
1746 |
{
|
1747 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1749,7 +1967,8 @@
|
|
1749 |
"target_language": "ita_Latn",
|
1750 |
"target_language_name": "Italian",
|
1751 |
"speakers": 64819790,
|
1752 |
-
"bleu": 69.15883435724486
|
|
|
1753 |
},
|
1754 |
{
|
1755 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1757,23 +1976,35 @@
|
|
1757 |
"target_language": "spa_Latn",
|
1758 |
"target_language_name": "Spanish",
|
1759 |
"speakers": 485000000,
|
1760 |
-
"bleu": 63.84670733785411
|
|
|
1761 |
},
|
1762 |
{
|
1763 |
"model": "anthropic/claude-3.5-sonnet",
|
1764 |
"original_language": "eng_Latn",
|
1765 |
"target_language": "ydd_Hebr",
|
1766 |
-
"target_language_name": "
|
1767 |
"speakers": 0,
|
1768 |
-
"bleu":
|
|
|
1769 |
},
|
1770 |
{
|
1771 |
"model": "anthropic/claude-3.5-sonnet",
|
1772 |
"original_language": "eng_Latn",
|
1773 |
"target_language": "gaz_Latn",
|
1774 |
-
"target_language_name": "
|
1775 |
"speakers": 0,
|
1776 |
-
"bleu":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1777 |
},
|
1778 |
{
|
1779 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1781,7 +2012,8 @@
|
|
1781 |
"target_language": "ktu_Latn",
|
1782 |
"target_language_name": "Kituba (Democratic Republic of the Congo)",
|
1783 |
"speakers": 0,
|
1784 |
-
"bleu": 52.848460160201476
|
|
|
1785 |
},
|
1786 |
{
|
1787 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1789,7 +2021,8 @@
|
|
1789 |
"target_language": "dyu_Latn",
|
1790 |
"target_language_name": "Jula",
|
1791 |
"speakers": 2700000,
|
1792 |
-
"bleu": 29.541518029704612
|
|
|
1793 |
},
|
1794 |
{
|
1795 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1797,15 +2030,17 @@
|
|
1797 |
"target_language": "ace_Latn",
|
1798 |
"target_language_name": "Aceh",
|
1799 |
"speakers": 3500032,
|
1800 |
-
"bleu": 54.98266447488466
|
|
|
1801 |
},
|
1802 |
{
|
1803 |
"model": "anthropic/claude-3.5-sonnet",
|
1804 |
"original_language": "eng_Latn",
|
1805 |
"target_language": "ckb_Arab",
|
1806 |
-
"target_language_name": "
|
1807 |
"speakers": 7250000,
|
1808 |
-
"bleu":
|
|
|
1809 |
},
|
1810 |
{
|
1811 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1813,7 +2048,8 @@
|
|
1813 |
"target_language": "mos_Latn",
|
1814 |
"target_language_name": "Moore",
|
1815 |
"speakers": 7600000,
|
1816 |
-
"bleu": 32.845809798291015
|
|
|
1817 |
},
|
1818 |
{
|
1819 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1821,7 +2057,8 @@
|
|
1821 |
"target_language": "kir_Cyrl",
|
1822 |
"target_language_name": "Kyrgyz",
|
1823 |
"speakers": 4568480,
|
1824 |
-
"bleu": 57.082442245268965
|
|
|
1825 |
},
|
1826 |
{
|
1827 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1829,7 +2066,8 @@
|
|
1829 |
"target_language": "npi_Deva",
|
1830 |
"target_language_name": "Nepali",
|
1831 |
"speakers": 0,
|
1832 |
-
"bleu": 55.29193473519464
|
|
|
1833 |
},
|
1834 |
{
|
1835 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1837,7 +2075,8 @@
|
|
1837 |
"target_language": "kbp_Latn",
|
1838 |
"target_language_name": "Kabiyè",
|
1839 |
"speakers": 1000000,
|
1840 |
-
"bleu": 22.549850465519835
|
|
|
1841 |
},
|
1842 |
{
|
1843 |
"model": "anthropic/claude-3.5-sonnet",
|
@@ -1845,6 +2084,7 @@
|
|
1845 |
"target_language": "bem_Latn",
|
1846 |
"target_language_name": "Bemba",
|
1847 |
"speakers": 3600000,
|
1848 |
-
"bleu": 47.80685489558032
|
|
|
1849 |
}
|
1850 |
]
|
|
|
5 |
"target_language": "tur_Latn",
|
6 |
"target_language_name": "Turkish",
|
7 |
"speakers": 82231620,
|
8 |
+
"bleu": 67.16006256755001,
|
9 |
+
"bert_score": 0.9309494157632192
|
10 |
},
|
11 |
{
|
12 |
"model": "anthropic/claude-3.5-sonnet",
|
13 |
"original_language": "eng_Latn",
|
14 |
"target_language": "ary_Arab",
|
15 |
+
"target_language_name": "Moroccan Arabic",
|
16 |
"speakers": 27500000,
|
17 |
+
"bleu": 49.308297678095336,
|
18 |
+
"bert_score": 0.9317501008510589
|
19 |
},
|
20 |
{
|
21 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
23 |
"target_language": "fij_Latn",
|
24 |
"target_language_name": "Fijian",
|
25 |
"speakers": 341270,
|
26 |
+
"bleu": 58.28926672457303,
|
27 |
+
"bert_score": 0.9183188617229462
|
28 |
},
|
29 |
{
|
30 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
32 |
"target_language": "lug_Latn",
|
33 |
"target_language_name": "Ganda",
|
34 |
"speakers": 4100000,
|
35 |
+
"bleu": 45.86933229358203,
|
36 |
+
"bert_score": 0.8834402799606323
|
37 |
},
|
38 |
{
|
39 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
41 |
"target_language": "kin_Latn",
|
42 |
"target_language_name": "Kinyarwanda",
|
43 |
"speakers": 12100000,
|
44 |
+
"bleu": 57.241062675597036,
|
45 |
+
"bert_score": 0.9069234490394592
|
46 |
},
|
47 |
{
|
48 |
"model": "openai/gpt-4o-mini",
|
|
|
50 |
"target_language": "ind_Latn",
|
51 |
"target_language_name": "Indonesian",
|
52 |
"speakers": 198996550,
|
53 |
+
"bleu": 76.69607051201163,
|
54 |
+
"bert_score": 0.9437516768773396
|
55 |
},
|
56 |
{
|
57 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
59 |
"target_language": "ind_Latn",
|
60 |
"target_language_name": "Indonesian",
|
61 |
"speakers": 198996550,
|
62 |
+
"bleu": 75.20007995551391,
|
63 |
+
"bert_score": 0.9425927738348643
|
64 |
},
|
65 |
{
|
66 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
|
|
68 |
"target_language": "ind_Latn",
|
69 |
"target_language_name": "Indonesian",
|
70 |
"speakers": 198996550,
|
71 |
+
"bleu": 74.1959714053824,
|
72 |
+
"bert_score": 0.9384953796863555
|
73 |
},
|
74 |
{
|
75 |
"model": "mistralai/mistral-nemo",
|
|
|
77 |
"target_language": "ind_Latn",
|
78 |
"target_language_name": "Indonesian",
|
79 |
"speakers": 198996550,
|
80 |
+
"bleu": 65.59558256613556,
|
81 |
+
"bert_score": 0.894232589006424
|
82 |
},
|
83 |
{
|
84 |
"model": "qwen/qwen-2.5-72b-instruct",
|
|
|
86 |
"target_language": "ind_Latn",
|
87 |
"target_language_name": "Indonesian",
|
88 |
"speakers": 198996550,
|
89 |
+
"bleu": 72.85582869172275,
|
90 |
+
"bert_score": 0.9316293319066365
|
91 |
},
|
92 |
{
|
93 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
95 |
"target_language": "nus_Latn",
|
96 |
"target_language_name": "Nuer",
|
97 |
"speakers": 900000,
|
98 |
+
"bleu": 16.57969879511241,
|
99 |
+
"bert_score": 0.8528214693069458
|
100 |
},
|
101 |
{
|
102 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
104 |
"target_language": "szl_Latn",
|
105 |
"target_language_name": "Silesian",
|
106 |
"speakers": 522000,
|
107 |
+
"bleu": 56.78363920686616,
|
108 |
+
"bert_score": 0.9106028735637665
|
109 |
},
|
110 |
{
|
111 |
"model": "anthropic/claude-3.5-sonnet",
|
112 |
"original_language": "eng_Latn",
|
113 |
"target_language": "azj_Latn",
|
114 |
+
"target_language_name": "North Azerbaijani",
|
115 |
"speakers": 9220610,
|
116 |
+
"bleu": 55.52651070626997,
|
117 |
+
"bert_score": 0.9145456314086914
|
118 |
},
|
119 |
{
|
120 |
"model": "anthropic/claude-3.5-sonnet",
|
121 |
"original_language": "eng_Latn",
|
122 |
"target_language": "dik_Latn",
|
123 |
+
"target_language_name": "Southwestern Dinka",
|
124 |
"speakers": 0,
|
125 |
+
"bleu": 17.591328140326063,
|
126 |
+
"bert_score": 0.8016291638215383
|
127 |
},
|
128 |
{
|
129 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
131 |
"target_language": "smo_Latn",
|
132 |
"target_language_name": "Samoan",
|
133 |
"speakers": 415720,
|
134 |
+
"bleu": 56.71388314225869,
|
135 |
+
"bert_score": 0.9166683554649353
|
136 |
},
|
137 |
{
|
138 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
140 |
"target_language": "heb_Hebr",
|
141 |
"target_language_name": "Hebrew",
|
142 |
"speakers": 9303950,
|
143 |
+
"bleu": 72.0702990513479,
|
144 |
+
"bert_score": 0.9640646179517111
|
145 |
},
|
146 |
{
|
147 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
149 |
"target_language": "lao_Laoo",
|
150 |
"target_language_name": "Lao",
|
151 |
"speakers": 5225552,
|
152 |
+
"bleu": 60.02109096770294,
|
153 |
+
"bert_score": 0.904438438018163
|
154 |
},
|
155 |
{
|
156 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
158 |
"target_language": "bul_Cyrl",
|
159 |
"target_language_name": "Bulgarian",
|
160 |
"speakers": 9000000,
|
161 |
+
"bleu": 72.9695925130979,
|
162 |
+
"bert_score": 0.9545443177223205
|
163 |
},
|
164 |
{
|
165 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
167 |
"target_language": "dgo_Deva",
|
168 |
"target_language_name": "Dogri",
|
169 |
"speakers": 2000000,
|
170 |
+
"bleu": 44.91535352779186,
|
171 |
+
"bert_score": 0.9340701540311177
|
172 |
},
|
173 |
{
|
174 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
176 |
"target_language": "epo_Latn",
|
177 |
"target_language_name": "Esperanto",
|
178 |
"speakers": 2000000,
|
179 |
+
"bleu": 69.60565775541012,
|
180 |
+
"bert_score": 0.9302131255467733
|
181 |
},
|
182 |
{
|
183 |
"model": "anthropic/claude-3.5-sonnet",
|
184 |
"original_language": "eng_Latn",
|
185 |
"target_language": "azb_Arab",
|
186 |
+
"target_language_name": "South Azerbaijani",
|
187 |
"speakers": 15000000,
|
188 |
+
"bleu": 44.37128043020771,
|
189 |
+
"bert_score": 0.9420697371164958
|
190 |
},
|
191 |
{
|
192 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
194 |
"target_language": "pap_Latn",
|
195 |
"target_language_name": "Papiamentu",
|
196 |
"speakers": 321300,
|
197 |
+
"bleu": 69.79553281331113,
|
198 |
+
"bert_score": 0.9325902322928111
|
199 |
},
|
200 |
{
|
201 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
203 |
"target_language": "ces_Latn",
|
204 |
"target_language_name": "Czech",
|
205 |
"speakers": 10700000,
|
206 |
+
"bleu": 69.71122905993063,
|
207 |
+
"bert_score": 0.9384464244047801
|
208 |
},
|
209 |
{
|
210 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
212 |
"target_language": "gle_Latn",
|
213 |
"target_language_name": "Irish",
|
214 |
"speakers": 1030000,
|
215 |
+
"bleu": 69.97251945242859,
|
216 |
+
"bert_score": 0.9440232972304027
|
217 |
},
|
218 |
{
|
219 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
221 |
"target_language": "cym_Latn",
|
222 |
"target_language_name": "Welsh",
|
223 |
"speakers": 977366,
|
224 |
+
"bleu": 83.34377244735965,
|
225 |
+
"bert_score": 0.9662299533685048
|
226 |
},
|
227 |
{
|
228 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
230 |
"target_language": "war_Latn",
|
231 |
"target_language_name": "Waray-Waray",
|
232 |
"speakers": 3100000,
|
233 |
+
"bleu": 66.38502312428538,
|
234 |
+
"bert_score": 0.920412007967631
|
235 |
},
|
236 |
{
|
237 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
239 |
"target_language": "tuk_Latn",
|
240 |
"target_language_name": "Turkmen",
|
241 |
"speakers": 16000000,
|
242 |
+
"bleu": 60.559370593640274,
|
243 |
+
"bert_score": 0.9125106473763783
|
244 |
},
|
245 |
{
|
246 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
248 |
"target_language": "kea_Latn",
|
249 |
"target_language_name": "Kabuverdianu",
|
250 |
"speakers": 871000,
|
251 |
+
"bleu": 65.11060103907447,
|
252 |
+
"bert_score": 0.921340302626292
|
253 |
},
|
254 |
{
|
255 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
257 |
"target_language": "swe_Latn",
|
258 |
"target_language_name": "Swedish",
|
259 |
"speakers": 9244250,
|
260 |
+
"bleu": 77.42161024703672,
|
261 |
+
"bert_score": 0.9571870168050131
|
262 |
},
|
263 |
{
|
264 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
266 |
"target_language": "mni_Mtei",
|
267 |
"target_language_name": "Meitei",
|
268 |
"speakers": 1470000,
|
269 |
+
"bleu": 41.90750872077243,
|
270 |
+
"bert_score": 0.9731392125288646
|
271 |
},
|
272 |
{
|
273 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
275 |
"target_language": "kan_Knda",
|
276 |
"target_language_name": "Kannada",
|
277 |
"speakers": 43600000,
|
278 |
+
"bleu": 60.01420283321725,
|
279 |
+
"bert_score": 0.9730932295322419
|
280 |
},
|
281 |
{
|
282 |
"model": "anthropic/claude-3.5-sonnet",
|
283 |
"original_language": "eng_Latn",
|
284 |
"target_language": "plt_Latn",
|
285 |
+
"target_language_name": "Merina Malagasy",
|
286 |
"speakers": 0,
|
287 |
+
"bleu": 61.096843454641544,
|
288 |
+
"bert_score": 0.9032936791578928
|
289 |
},
|
290 |
{
|
291 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
293 |
"target_language": "ewe_Latn",
|
294 |
"target_language_name": "Éwé",
|
295 |
"speakers": 3000000,
|
296 |
+
"bleu": 41.6614038790914,
|
297 |
+
"bert_score": 0.8829316159089406
|
298 |
},
|
299 |
{
|
300 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
302 |
"target_language": "rus_Cyrl",
|
303 |
"target_language_name": "Russian",
|
304 |
"speakers": 171428900,
|
305 |
+
"bleu": 71.14894410390329,
|
306 |
+
"bert_score": 0.9518508851528168
|
307 |
},
|
308 |
{
|
309 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
311 |
"target_language": "bjn_Arab",
|
312 |
"target_language_name": "Banjar",
|
313 |
"speakers": 3500000,
|
314 |
+
"bleu": 36.7812759423696,
|
315 |
+
"bert_score": 0.9300645053386688
|
316 |
},
|
317 |
{
|
318 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
320 |
"target_language": "kmb_Latn",
|
321 |
"target_language_name": "Kimbundu",
|
322 |
"speakers": 0,
|
323 |
+
"bleu": 5.85234572235619,
|
324 |
+
"bert_score": 0.6849321782588959
|
325 |
},
|
326 |
{
|
327 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
329 |
"target_language": "vec_Latn",
|
330 |
"target_language_name": "Venetian",
|
331 |
"speakers": 2000000,
|
332 |
+
"bleu": 60.61408762705794,
|
333 |
+
"bert_score": 0.9080212533473968
|
334 |
},
|
335 |
{
|
336 |
"model": "anthropic/claude-3.5-sonnet",
|
337 |
"original_language": "eng_Latn",
|
338 |
"target_language": "aeb_Arab",
|
339 |
+
"target_language_name": "Tunisian Arabic",
|
340 |
"speakers": 11600000,
|
341 |
+
"bleu": 49.67140907439696,
|
342 |
+
"bert_score": 0.9337966998418172
|
343 |
},
|
344 |
{
|
345 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
347 |
"target_language": "lit_Latn",
|
348 |
"target_language_name": "Lithuanian",
|
349 |
"speakers": 4000000,
|
350 |
+
"bleu": 67.16256955707802,
|
351 |
+
"bert_score": 0.915470290184021
|
352 |
},
|
353 |
{
|
354 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
356 |
"target_language": "swh_Latn",
|
357 |
"target_language_name": "Swahili",
|
358 |
"speakers": 82300000,
|
359 |
+
"bleu": 73.51990421418041,
|
360 |
+
"bert_score": 0.9450787365436554
|
361 |
},
|
362 |
{
|
363 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
365 |
"target_language": "bug_Latn",
|
366 |
"target_language_name": "Bugis",
|
367 |
"speakers": 5017800,
|
368 |
+
"bleu": 44.838817003109384,
|
369 |
+
"bert_score": 0.864792396624883
|
370 |
},
|
371 |
{
|
372 |
"model": "anthropic/claude-3.5-sonnet",
|
373 |
"original_language": "eng_Latn",
|
374 |
"target_language": "apc_Arab_nort3139",
|
375 |
+
"target_language_name": "Levantine Arabic",
|
376 |
"speakers": 44000000,
|
377 |
+
"bleu": 55.944015565916516,
|
378 |
+
"bert_score": 0.9422544419765473
|
379 |
},
|
380 |
{
|
381 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
383 |
"target_language": "lus_Latn",
|
384 |
"target_language_name": "Mizo",
|
385 |
"speakers": 500000,
|
386 |
+
"bleu": 51.65580174875804,
|
387 |
+
"bert_score": 0.8875152905782063
|
388 |
},
|
389 |
{
|
390 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
392 |
"target_language": "lim_Latn",
|
393 |
"target_language_name": "Limburgish",
|
394 |
"speakers": 1600000,
|
395 |
+
"bleu": 59.44855049817084,
|
396 |
+
"bert_score": 0.8987095455328623
|
397 |
},
|
398 |
{
|
399 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
401 |
"target_language": "mri_Latn",
|
402 |
"target_language_name": "Maori",
|
403 |
"speakers": 160000,
|
404 |
+
"bleu": 54.831993564329125,
|
405 |
+
"bert_score": 0.9185245017210643
|
406 |
},
|
407 |
{
|
408 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
410 |
"target_language": "kam_Latn",
|
411 |
"target_language_name": "Kamba",
|
412 |
"speakers": 3893000,
|
413 |
+
"bleu": 41.73348967095708,
|
414 |
+
"bert_score": 0.8780206362406413
|
415 |
},
|
416 |
{
|
417 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
419 |
"target_language": "ban_Latn",
|
420 |
"target_language_name": "Bali (Indonesia)",
|
421 |
"speakers": 4000000,
|
422 |
+
"bleu": 52.87524191594727,
|
423 |
+
"bert_score": 0.8934772113958994
|
424 |
},
|
425 |
{
|
426 |
"model": "anthropic/claude-3.5-sonnet",
|
427 |
"original_language": "eng_Latn",
|
428 |
"target_language": "pan_Guru",
|
429 |
+
"target_language_name": "Eastern Punjabi",
|
430 |
"speakers": 125000000,
|
431 |
+
"bleu": 60.46844110900072,
|
432 |
+
"bert_score": 0.9882440070311228
|
433 |
},
|
434 |
{
|
435 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
437 |
"target_language": "por_Latn",
|
438 |
"target_language_name": "Portuguese",
|
439 |
"speakers": 254300000,
|
440 |
+
"bleu": 77.49780742224304,
|
441 |
+
"bert_score": 0.9494876027107239
|
442 |
},
|
443 |
{
|
444 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
446 |
"target_language": "crh_Latn",
|
447 |
"target_language_name": "Crimean Tatar",
|
448 |
"speakers": 552740,
|
449 |
+
"bleu": 52.705024944759934,
|
450 |
+
"bert_score": 0.8972040812174479
|
451 |
},
|
452 |
{
|
453 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
455 |
"target_language": "srp_Cyrl",
|
456 |
"target_language_name": "Serbian",
|
457 |
"speakers": 9000000,
|
458 |
+
"bleu": 69.96913961762156,
|
459 |
+
"bert_score": 0.9582955678304036
|
460 |
},
|
461 |
{
|
462 |
"model": "openai/gpt-4o-mini",
|
|
|
464 |
"target_language": "kas_Deva",
|
465 |
"target_language_name": "Kashmiri",
|
466 |
"speakers": 6900000,
|
467 |
+
"bleu": 22.94872648513265,
|
468 |
+
"bert_score": 0.9032864511013031
|
469 |
},
|
470 |
{
|
471 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
473 |
"target_language": "kas_Deva",
|
474 |
"target_language_name": "Kashmiri",
|
475 |
"speakers": 6900000,
|
476 |
+
"bleu": 27.525562771983658,
|
477 |
+
"bert_score": 0.9144352018833161
|
478 |
},
|
479 |
{
|
480 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
|
|
482 |
"target_language": "kas_Deva",
|
483 |
"target_language_name": "Kashmiri",
|
484 |
"speakers": 6900000,
|
485 |
+
"bleu": 7.999053096113321,
|
486 |
+
"bert_score": 0.891643617550532
|
487 |
},
|
488 |
{
|
489 |
"model": "mistralai/mistral-nemo",
|
|
|
491 |
"target_language": "kas_Deva",
|
492 |
"target_language_name": "Kashmiri",
|
493 |
"speakers": 6900000,
|
494 |
+
"bleu": 15.126083511737422,
|
495 |
+
"bert_score": 0.8491478403409322
|
496 |
},
|
497 |
{
|
498 |
"model": "qwen/qwen-2.5-72b-instruct",
|
|
|
500 |
"target_language": "kas_Deva",
|
501 |
"target_language_name": "Kashmiri",
|
502 |
"speakers": 6900000,
|
503 |
+
"bleu": 21.928943407791756,
|
504 |
+
"bert_score": 0.9002275844415029
|
505 |
},
|
506 |
{
|
507 |
"model": "anthropic/claude-3.5-sonnet",
|
508 |
"original_language": "eng_Latn",
|
509 |
"target_language": "bod_Tibt",
|
510 |
+
"target_language_name": "Central Tibetan",
|
511 |
"speakers": 1200000,
|
512 |
+
"bleu": 51.34907527401463,
|
513 |
+
"bert_score": 0.9671575029691061
|
514 |
},
|
515 |
{
|
516 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
518 |
"target_language": "slv_Latn",
|
519 |
"target_language_name": "Slovene",
|
520 |
"speakers": 2400000,
|
521 |
+
"bleu": 72.56912707571306,
|
522 |
+
"bert_score": 0.9432346244653066
|
523 |
},
|
524 |
{
|
525 |
"model": "anthropic/claude-3.5-sonnet",
|
526 |
"original_language": "eng_Latn",
|
527 |
"target_language": "ars_Arab",
|
528 |
+
"target_language_name": "Najdi Arabic",
|
529 |
"speakers": 0,
|
530 |
+
"bleu": 46.41024303772761,
|
531 |
+
"bert_score": 0.9332984228928883
|
532 |
},
|
533 |
{
|
534 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
536 |
"target_language": "cat_Latn",
|
537 |
"target_language_name": "Catalan",
|
538 |
"speakers": 5100000,
|
539 |
+
"bleu": 74.45950079317922,
|
540 |
+
"bert_score": 0.9464139262835185
|
541 |
},
|
542 |
{
|
543 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
545 |
"target_language": "zul_Latn",
|
546 |
"target_language_name": "Zulu",
|
547 |
"speakers": 15700000,
|
548 |
+
"bleu": 59.176207838896076,
|
549 |
+
"bert_score": 0.9099391102790833
|
550 |
},
|
551 |
{
|
552 |
"model": "anthropic/claude-3.5-sonnet",
|
553 |
"original_language": "eng_Latn",
|
554 |
"target_language": "pes_Arab",
|
555 |
+
"target_language_name": "Iranian Persian",
|
556 |
"speakers": 52800000,
|
557 |
+
"bleu": 57.64441696979444,
|
558 |
+
"bert_score": 0.9476486345132192
|
559 |
},
|
560 |
{
|
561 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
563 |
"target_language": "taq_Latn",
|
564 |
"target_language_name": "Tamasheq",
|
565 |
"speakers": 500000,
|
566 |
+
"bleu": 25.866944911127725,
|
567 |
+
"bert_score": 0.8280646105607351
|
568 |
},
|
569 |
{
|
570 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
572 |
"target_language": "snd_Deva",
|
573 |
"target_language_name": "Sindhi",
|
574 |
"speakers": 25000000,
|
575 |
+
"bleu": 40.04493401977834,
|
576 |
+
"bert_score": 0.9263754248619079
|
577 |
},
|
578 |
{
|
579 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
581 |
"target_language": "ssw_Latn",
|
582 |
"target_language_name": "Swati",
|
583 |
"speakers": 2034200,
|
584 |
+
"bleu": 52.77460964391619,
|
585 |
+
"bert_score": 0.8899940272172292
|
586 |
},
|
587 |
{
|
588 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
590 |
"target_language": "mkd_Cyrl",
|
591 |
"target_language_name": "Macedonian",
|
592 |
"speakers": 2000000,
|
593 |
+
"bleu": 72.27334714365769,
|
594 |
+
"bert_score": 0.9558346649010976
|
595 |
},
|
596 |
{
|
597 |
"model": "openai/gpt-4o-mini",
|
|
|
599 |
"target_language": "pol_Latn",
|
600 |
"target_language_name": "Polish",
|
601 |
"speakers": 40200000,
|
602 |
+
"bleu": 63.79524354957938,
|
603 |
+
"bert_score": 0.9248784482479095
|
604 |
},
|
605 |
{
|
606 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
608 |
"target_language": "pol_Latn",
|
609 |
"target_language_name": "Polish",
|
610 |
"speakers": 40200000,
|
611 |
+
"bleu": 65.97562270518736,
|
612 |
+
"bert_score": 0.9295462707678477
|
613 |
},
|
614 |
{
|
615 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
|
|
617 |
"target_language": "pol_Latn",
|
618 |
"target_language_name": "Polish",
|
619 |
"speakers": 40200000,
|
620 |
+
"bleu": 62.09512880944625,
|
621 |
+
"bert_score": 0.918810615936915
|
622 |
},
|
623 |
{
|
624 |
"model": "mistralai/mistral-nemo",
|
|
|
626 |
"target_language": "pol_Latn",
|
627 |
"target_language_name": "Polish",
|
628 |
"speakers": 40200000,
|
629 |
+
"bleu": 56.42877796144466,
|
630 |
+
"bert_score": 0.8988153100013733
|
631 |
},
|
632 |
{
|
633 |
"model": "qwen/qwen-2.5-72b-instruct",
|
|
|
635 |
"target_language": "pol_Latn",
|
636 |
"target_language_name": "Polish",
|
637 |
"speakers": 40200000,
|
638 |
+
"bleu": 61.08942681151859,
|
639 |
+
"bert_score": 0.9175748288631439
|
640 |
},
|
641 |
{
|
642 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
644 |
"target_language": "srd_Latn",
|
645 |
"target_language_name": "Sardinian",
|
646 |
"speakers": 1300000,
|
647 |
+
"bleu": 62.69039147714039,
|
648 |
+
"bert_score": 0.9118991812070211
|
649 |
},
|
650 |
{
|
651 |
"model": "anthropic/claude-3.5-sonnet",
|
652 |
"original_language": "eng_Latn",
|
653 |
"target_language": "arb_Latn",
|
654 |
+
"target_language_name": "Standard Arabic",
|
655 |
"speakers": 0,
|
656 |
+
"bleu": 48.72485475113871,
|
657 |
+
"bert_score": 0.8800670305887858
|
658 |
},
|
659 |
{
|
660 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
662 |
"target_language": "twi_Latn_asan1239",
|
663 |
"target_language_name": "Twi",
|
664 |
"speakers": 3000000,
|
665 |
+
"bleu": 44.44337481309101,
|
666 |
+
"bert_score": 0.8881823480129242
|
667 |
},
|
668 |
{
|
669 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
671 |
"target_language": "tum_Latn",
|
672 |
"target_language_name": "Tumbuka",
|
673 |
"speakers": 2680000,
|
674 |
+
"bleu": 44.0490017392109,
|
675 |
+
"bert_score": 0.8865564326445262
|
676 |
},
|
677 |
{
|
678 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
680 |
"target_language": "fur_Latn",
|
681 |
"target_language_name": "Friulian",
|
682 |
"speakers": 300000,
|
683 |
+
"bleu": 66.54880923723718,
|
684 |
+
"bert_score": 0.9255799611409505
|
685 |
},
|
686 |
{
|
687 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
689 |
"target_language": "lua_Latn",
|
690 |
"target_language_name": "Luba-Kasai",
|
691 |
"speakers": 6300000,
|
692 |
+
"bleu": 45.065529165477344,
|
693 |
+
"bert_score": 0.8749240279197693
|
694 |
},
|
695 |
{
|
696 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
698 |
"target_language": "fil_Latn",
|
699 |
"target_language_name": "Filipino",
|
700 |
"speakers": 90000000,
|
701 |
+
"bleu": 70.19284983784472,
|
702 |
+
"bert_score": 0.92694251537323
|
703 |
},
|
704 |
{
|
705 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
707 |
"target_language": "afr_Latn",
|
708 |
"target_language_name": "Afrikaans",
|
709 |
"speakers": 10300000,
|
710 |
+
"bleu": 76.89005407773752,
|
711 |
+
"bert_score": 0.9481831173102061
|
712 |
},
|
713 |
{
|
714 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
716 |
"target_language": "bos_Latn",
|
717 |
"target_language_name": "Bosnian",
|
718 |
"speakers": 3500000,
|
719 |
+
"bleu": 72.54880271311463,
|
720 |
+
"bert_score": 0.94769393603007
|
721 |
},
|
722 |
{
|
723 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
725 |
"target_language": "ltg_Latn",
|
726 |
"target_language_name": "Latgalian",
|
727 |
"speakers": 200000,
|
728 |
+
"bleu": 56.484355652391756,
|
729 |
+
"bert_score": 0.9078494012355804
|
730 |
},
|
731 |
{
|
732 |
"model": "anthropic/claude-3.5-sonnet",
|
733 |
"original_language": "eng_Latn",
|
734 |
"target_language": "acq_Arab",
|
735 |
+
"target_language_name": "Ta’izzi-Adeni Arabic",
|
736 |
"speakers": 10500000,
|
737 |
+
"bleu": 49.413933528139225,
|
738 |
+
"bert_score": 0.9354432185490926
|
739 |
},
|
740 |
{
|
741 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
743 |
"target_language": "mag_Deva",
|
744 |
"target_language_name": "Magahi",
|
745 |
"speakers": 20700000,
|
746 |
+
"bleu": 58.54742215461198,
|
747 |
+
"bert_score": 0.9458349565664927
|
748 |
},
|
749 |
{
|
750 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
752 |
"target_language": "min_Latn",
|
753 |
"target_language_name": "Minangkabau",
|
754 |
"speakers": 5530000,
|
755 |
+
"bleu": 64.0323403919738,
|
756 |
+
"bert_score": 0.9164695799350738
|
757 |
},
|
758 |
{
|
759 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
761 |
"target_language": "kor_Hang",
|
762 |
"target_language_name": "Korean",
|
763 |
"speakers": 77300000,
|
764 |
+
"bleu": 43.68722859743311,
|
765 |
+
"bert_score": 0.9579092760880789
|
766 |
},
|
767 |
{
|
768 |
"model": "anthropic/claude-3.5-sonnet",
|
769 |
"original_language": "eng_Latn",
|
770 |
"target_language": "zsm_Latn",
|
771 |
+
"target_language_name": "Standard Malay",
|
772 |
"speakers": 0,
|
773 |
+
"bleu": 74.2657232797885,
|
774 |
+
"bert_score": 0.9445500493049621
|
775 |
},
|
776 |
{
|
777 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
779 |
"target_language": "mar_Deva",
|
780 |
"target_language_name": "Marathi",
|
781 |
"speakers": 83100000,
|
782 |
+
"bleu": 57.44340907113495,
|
783 |
+
"bert_score": 0.9421781261761983
|
784 |
},
|
785 |
{
|
786 |
"model": "anthropic/claude-3.5-sonnet",
|
787 |
"original_language": "eng_Latn",
|
788 |
"target_language": "pbt_Arab",
|
789 |
+
"target_language_name": "Southern Pashto",
|
790 |
"speakers": 10900000,
|
791 |
+
"bleu": 38.3124819373775,
|
792 |
+
"bert_score": 0.9212681790192921
|
793 |
},
|
794 |
{
|
795 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
797 |
"target_language": "lij_Latn",
|
798 |
"target_language_name": "Ligurian",
|
799 |
"speakers": 500000,
|
800 |
+
"bleu": 55.85306363017816,
|
801 |
+
"bert_score": 0.904762077331543
|
802 |
},
|
803 |
{
|
804 |
"model": "anthropic/claude-3.5-sonnet",
|
805 |
"original_language": "eng_Latn",
|
806 |
"target_language": "knc_Latn",
|
807 |
+
"target_language_name": "Yerwa Kanuri",
|
808 |
"speakers": 0,
|
809 |
+
"bleu": 22.062110974228755,
|
810 |
+
"bert_score": 0.8124950389067332
|
811 |
},
|
812 |
{
|
813 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
815 |
"target_language": "chv_Cyrl",
|
816 |
"target_language_name": "Chuvash",
|
817 |
"speakers": 1279650,
|
818 |
+
"bleu": 45.05466587233098,
|
819 |
+
"bert_score": 0.9203916192054749
|
820 |
},
|
821 |
{
|
822 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
824 |
"target_language": "asm_Beng",
|
825 |
"target_language_name": "Assamese",
|
826 |
"speakers": 15300000,
|
827 |
+
"bleu": 47.03513316051628,
|
828 |
+
"bert_score": 0.9281195739905039
|
829 |
},
|
830 |
{
|
831 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
833 |
"target_language": "ace_Arab",
|
834 |
"target_language_name": "Aceh",
|
835 |
"speakers": 3500032,
|
836 |
+
"bleu": 23.349267705271775,
|
837 |
+
"bert_score": 0.8943273961544037
|
838 |
},
|
839 |
{
|
840 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
842 |
"target_language": "tha_Thai",
|
843 |
"target_language_name": "Thai",
|
844 |
"speakers": 40000000,
|
845 |
+
"bleu": 62.81253609435389,
|
846 |
+
"bert_score": 0.9225328485171
|
847 |
},
|
848 |
{
|
849 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
851 |
"target_language": "fao_Latn",
|
852 |
"target_language_name": "Faroese",
|
853 |
"speakers": 69150,
|
854 |
+
"bleu": 65.91479024829229,
|
855 |
+
"bert_score": 0.9332413752873738
|
856 |
},
|
857 |
{
|
858 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
860 |
"target_language": "nqo_Nkoo",
|
861 |
"target_language_name": "N’Ko",
|
862 |
"speakers": 0,
|
863 |
+
"bleu": 32.48349079900792,
|
864 |
+
"bert_score": 0.9823745767275492
|
865 |
},
|
866 |
{
|
867 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
869 |
"target_language": "ilo_Latn",
|
870 |
"target_language_name": "Ilocano",
|
871 |
"speakers": 9100000,
|
872 |
+
"bleu": 62.605886459379576,
|
873 |
+
"bert_score": 0.9115280091762543
|
874 |
},
|
875 |
{
|
876 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
878 |
"target_language": "kat_Geor",
|
879 |
"target_language_name": "Georgian",
|
880 |
"speakers": 3700000,
|
881 |
+
"bleu": 61.016636144241765,
|
882 |
+
"bert_score": 0.9546662310759226
|
883 |
},
|
884 |
{
|
885 |
"model": "anthropic/claude-3.5-sonnet",
|
886 |
"original_language": "eng_Latn",
|
887 |
"target_language": "ayr_Latn",
|
888 |
+
"target_language_name": "Central Aymara",
|
889 |
"speakers": 0,
|
890 |
+
"bleu": 42.769843666920714,
|
891 |
+
"bert_score": 0.8625142018000285
|
892 |
},
|
893 |
{
|
894 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
896 |
"target_language": "dan_Latn",
|
897 |
"target_language_name": "Danish",
|
898 |
"speakers": 6000000,
|
899 |
+
"bleu": 78.0935433283814,
|
900 |
+
"bert_score": 0.9506490747133891
|
901 |
},
|
902 |
{
|
903 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
905 |
"target_language": "brx_Deva",
|
906 |
"target_language_name": "Boro (India)",
|
907 |
"speakers": 1482929,
|
908 |
+
"bleu": 36.11004749691388,
|
909 |
+
"bert_score": 0.9251878539721171
|
910 |
},
|
911 |
{
|
912 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
914 |
"target_language": "sag_Latn",
|
915 |
"target_language_name": "Sango",
|
916 |
"speakers": 4600000,
|
917 |
+
"bleu": 34.875422265717596,
|
918 |
+
"bert_score": 0.8720244228839874
|
919 |
},
|
920 |
{
|
921 |
"model": "anthropic/claude-3.5-sonnet",
|
922 |
"original_language": "eng_Latn",
|
923 |
"target_language": "lvs_Latn",
|
924 |
+
"target_language_name": "Standard Latvian",
|
925 |
"speakers": 0,
|
926 |
+
"bleu": 65.08332100371138,
|
927 |
+
"bert_score": 0.9217625757058462
|
928 |
},
|
929 |
{
|
930 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
932 |
"target_language": "jpn_Jpan",
|
933 |
"target_language_name": "Japanese",
|
934 |
"speakers": 128000000,
|
935 |
+
"bleu": 49.91661356931259,
|
936 |
+
"bert_score": 0.9425287286440531
|
937 |
},
|
938 |
{
|
939 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
941 |
"target_language": "uig_Arab",
|
942 |
"target_language_name": "Uyghur",
|
943 |
"speakers": 10400000,
|
944 |
+
"bleu": 53.53468771030665,
|
945 |
+
"bert_score": 0.9397906005382538
|
946 |
},
|
947 |
{
|
948 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
950 |
"target_language": "fra_Latn",
|
951 |
"target_language_name": "French",
|
952 |
"speakers": 208157220,
|
953 |
+
"bleu": 79.3023871219446,
|
954 |
+
"bert_score": 0.9554367423057556
|
955 |
},
|
956 |
{
|
957 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
959 |
"target_language": "jav_Latn",
|
960 |
"target_language_name": "Javanese",
|
961 |
"speakers": 84308740,
|
962 |
+
"bleu": 60.44033529900538,
|
963 |
+
"bert_score": 0.9125308076540629
|
964 |
},
|
965 |
{
|
966 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
968 |
"target_language": "sun_Latn",
|
969 |
"target_language_name": "Sunda",
|
970 |
"speakers": 32400000,
|
971 |
+
"bleu": 56.40659991041485,
|
972 |
+
"bert_score": 0.9077177822589875
|
973 |
},
|
974 |
{
|
975 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
977 |
"target_language": "umb_Latn",
|
978 |
"target_language_name": "Umbundu",
|
979 |
"speakers": 6000000,
|
980 |
+
"bleu": 21.080277559665817,
|
981 |
+
"bert_score": 0.8461364289124806
|
982 |
},
|
983 |
{
|
984 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
986 |
"target_language": "bel_Cyrl",
|
987 |
"target_language_name": "Belarusian",
|
988 |
"speakers": 7900000,
|
989 |
+
"bleu": 54.51951664423131,
|
990 |
+
"bert_score": 0.9329862594604492
|
991 |
},
|
992 |
{
|
993 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
995 |
"target_language": "cjk_Latn",
|
996 |
"target_language_name": "Chokwe",
|
997 |
"speakers": 0,
|
998 |
+
"bleu": 10.186407416077753,
|
999 |
+
"bert_score": 0.727788798014323
|
1000 |
},
|
1001 |
{
|
1002 |
"model": "anthropic/claude-3.5-sonnet",
|
1003 |
"original_language": "eng_Latn",
|
1004 |
"target_language": "yue_Hant",
|
1005 |
+
"target_language_name": "Yue Chinese",
|
1006 |
"speakers": 73100000,
|
1007 |
+
"bleu": 34.561465122815996,
|
1008 |
+
"bert_score": 0.9634495397408803
|
1009 |
},
|
1010 |
{
|
1011 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1013 |
"target_language": "hat_Latn",
|
1014 |
"target_language_name": "Haitian Creole",
|
1015 |
"speakers": 9600000,
|
1016 |
+
"bleu": 63.85321875910916,
|
1017 |
+
"bert_score": 0.9323611199855805
|
1018 |
},
|
1019 |
{
|
1020 |
"model": "anthropic/claude-3.5-sonnet",
|
1021 |
"original_language": "eng_Latn",
|
1022 |
"target_language": "kmr_Latn",
|
1023 |
+
"target_language_name": "Northern Kurdish",
|
1024 |
"speakers": 14600000,
|
1025 |
+
"bleu": 55.79658782267678,
|
1026 |
+
"bert_score": 0.9104436457157135
|
1027 |
},
|
1028 |
{
|
1029 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1031 |
"target_language": "ceb_Latn",
|
1032 |
"target_language_name": "Cebuano",
|
1033 |
"speakers": 15900000,
|
1034 |
+
"bleu": 69.455795865483,
|
1035 |
+
"bert_score": 0.932128123442332
|
1036 |
},
|
1037 |
{
|
1038 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1040 |
"target_language": "dzo_Tibt",
|
1041 |
"target_language_name": "Dzongkha",
|
1042 |
"speakers": 237080,
|
1043 |
+
"bleu": 44.35738140173861,
|
1044 |
+
"bert_score": 0.9664796074231465
|
1045 |
},
|
1046 |
{
|
1047 |
"model": "anthropic/claude-3.5-sonnet",
|
1048 |
"original_language": "eng_Latn",
|
1049 |
"target_language": "deu_Latn",
|
1050 |
+
"target_language_name": "Standard German",
|
1051 |
"speakers": 105000000,
|
1052 |
+
"bleu": 77.19665151067797,
|
1053 |
+
"bert_score": 0.9468763132890066
|
1054 |
},
|
1055 |
{
|
1056 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1058 |
"target_language": "ibo_Latn",
|
1059 |
"target_language_name": "Igbo",
|
1060 |
"speakers": 27000000,
|
1061 |
+
"bleu": 46.40173449341075,
|
1062 |
+
"bert_score": 0.9137314637502034
|
1063 |
},
|
1064 |
{
|
1065 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1067 |
"target_language": "vie_Latn",
|
1068 |
"target_language_name": "Vietnamese",
|
1069 |
"speakers": 76000000,
|
1070 |
+
"bleu": 70.35607494641172,
|
1071 |
+
"bert_score": 0.9527418712774912
|
1072 |
},
|
1073 |
{
|
1074 |
"model": "anthropic/claude-3.5-sonnet",
|
1075 |
"original_language": "eng_Latn",
|
1076 |
"target_language": "quy_Latn",
|
1077 |
+
"target_language_name": "Ayacucho Quechua",
|
1078 |
"speakers": 918200,
|
1079 |
+
"bleu": 45.653492702784725,
|
1080 |
+
"bert_score": 0.8731370111306508
|
1081 |
},
|
1082 |
{
|
1083 |
"model": "anthropic/claude-3.5-sonnet",
|
1084 |
"original_language": "eng_Latn",
|
1085 |
"target_language": "cmn_Hant",
|
1086 |
+
"target_language_name": "Mandarin Chinese",
|
1087 |
"speakers": 1074000000,
|
1088 |
+
"bleu": 41.61854589430943,
|
1089 |
+
"bert_score": 0.9654350221157074
|
1090 |
},
|
1091 |
{
|
1092 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1094 |
"target_language": "mai_Deva",
|
1095 |
"target_language_name": "Maithili",
|
1096 |
"speakers": 33900000,
|
1097 |
+
"bleu": 54.65300713908629,
|
1098 |
+
"bert_score": 0.9433513383070627
|
1099 |
},
|
1100 |
{
|
1101 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1103 |
"target_language": "gla_Latn",
|
1104 |
"target_language_name": "Scottish Gaelic",
|
1105 |
"speakers": 60130,
|
1106 |
+
"bleu": 62.604437133773324,
|
1107 |
+
"bert_score": 0.9264988481998444
|
1108 |
},
|
1109 |
{
|
1110 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1112 |
"target_language": "urd_Arab",
|
1113 |
"target_language_name": "Urdu",
|
1114 |
"speakers": 94022900,
|
1115 |
+
"bleu": 61.12554572717868,
|
1116 |
+
"bert_score": 0.9538880089918772
|
1117 |
},
|
1118 |
{
|
1119 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1121 |
"target_language": "shn_Mymr",
|
1122 |
"target_language_name": "Shan",
|
1123 |
"speakers": 3000000,
|
1124 |
+
"bleu": 29.21299485766884,
|
1125 |
+
"bert_score": 0.9378574808438619
|
1126 |
},
|
1127 |
{
|
1128 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1130 |
"target_language": "wol_Latn",
|
1131 |
"target_language_name": "Wolof",
|
1132 |
"speakers": 3700000,
|
1133 |
+
"bleu": 42.64301275691043,
|
1134 |
+
"bert_score": 0.8762976408004761
|
1135 |
},
|
1136 |
{
|
1137 |
"model": "anthropic/claude-3.5-sonnet",
|
1138 |
"original_language": "eng_Latn",
|
1139 |
"target_language": "cmn_Hans",
|
1140 |
+
"target_language_name": "Mandarin Chinese",
|
1141 |
"speakers": 1074000000,
|
1142 |
+
"bleu": 43.441487462618014,
|
1143 |
+
"bert_score": 0.9615364015102387
|
1144 |
},
|
1145 |
{
|
1146 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1148 |
"target_language": "guj_Gujr",
|
1149 |
"target_language_name": "Gujarati",
|
1150 |
"speakers": 56400000,
|
1151 |
+
"bleu": 55.588451345198735,
|
1152 |
+
"bert_score": 0.9753397226333618
|
1153 |
},
|
1154 |
{
|
1155 |
"model": "anthropic/claude-3.5-sonnet",
|
1156 |
"original_language": "eng_Latn",
|
1157 |
"target_language": "ekk_Latn",
|
1158 |
+
"target_language_name": "Standard Estonian",
|
1159 |
"speakers": 1164770,
|
1160 |
+
"bleu": 67.41569195167845,
|
1161 |
+
"bert_score": 0.9277306814988454
|
1162 |
},
|
1163 |
{
|
1164 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1166 |
"target_language": "luo_Latn",
|
1167 |
"target_language_name": "Dholuo",
|
1168 |
"speakers": 3000000,
|
1169 |
+
"bleu": 46.41194790710186,
|
1170 |
+
"bert_score": 0.8803233822186788
|
1171 |
},
|
1172 |
{
|
1173 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1175 |
"target_language": "hrv_Latn",
|
1176 |
"target_language_name": "Croatian",
|
1177 |
"speakers": 7000000,
|
1178 |
+
"bleu": 69.54569836615161,
|
1179 |
+
"bert_score": 0.9444877982139588
|
1180 |
},
|
1181 |
{
|
1182 |
"model": "anthropic/claude-3.5-sonnet",
|
1183 |
"original_language": "eng_Latn",
|
1184 |
"target_language": "uzn_Latn",
|
1185 |
+
"target_language_name": "Northern Uzbek",
|
1186 |
"speakers": 26912410,
|
1187 |
+
"bleu": 63.20557385096708,
|
1188 |
+
"bert_score": 0.9120756924152374
|
1189 |
},
|
1190 |
{
|
1191 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1193 |
"target_language": "ben_Beng",
|
1194 |
"target_language_name": "Bengali",
|
1195 |
"speakers": 300000000,
|
1196 |
+
"bleu": 57.14175888160181,
|
1197 |
+
"bert_score": 0.9483523646990458
|
1198 |
},
|
1199 |
{
|
1200 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1202 |
"target_language": "nya_Latn",
|
1203 |
"target_language_name": "Chichewa",
|
1204 |
"speakers": 12000000,
|
1205 |
+
"bleu": 59.76016801606614,
|
1206 |
+
"bert_score": 0.9069253901640574
|
1207 |
},
|
1208 |
{
|
1209 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1211 |
"target_language": "tsn_Latn",
|
1212 |
"target_language_name": "Setswana",
|
1213 |
"speakers": 4500000,
|
1214 |
+
"bleu": 55.22888902281337,
|
1215 |
+
"bert_score": 0.9117900888125102
|
1216 |
},
|
1217 |
{
|
1218 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1220 |
"target_language": "fin_Latn",
|
1221 |
"target_language_name": "Finnish",
|
1222 |
"speakers": 5413380,
|
1223 |
+
"bleu": 70.94250295175219,
|
1224 |
+
"bert_score": 0.9320579687754313
|
1225 |
},
|
1226 |
{
|
1227 |
"model": "anthropic/claude-3.5-sonnet",
|
1228 |
"original_language": "eng_Latn",
|
1229 |
"target_language": "nso_Latn",
|
1230 |
+
"target_language_name": "Northern Sotho",
|
1231 |
"speakers": 4100000,
|
1232 |
+
"bleu": 62.87694016917069,
|
1233 |
+
"bert_score": 0.9261207898457845
|
1234 |
},
|
1235 |
{
|
1236 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1238 |
"target_language": "sna_Latn",
|
1239 |
"target_language_name": "Shona",
|
1240 |
"speakers": 9023000,
|
1241 |
+
"bleu": 51.55921914049446,
|
1242 |
+
"bert_score": 0.8798740128676097
|
1243 |
},
|
1244 |
{
|
1245 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1247 |
"target_language": "snd_Arab",
|
1248 |
"target_language_name": "Sindhi",
|
1249 |
"speakers": 25000000,
|
1250 |
+
"bleu": 56.33027730975489,
|
1251 |
+
"bert_score": 0.9470286051432292
|
1252 |
},
|
1253 |
{
|
1254 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1256 |
"target_language": "xho_Latn",
|
1257 |
"target_language_name": "Xhosa",
|
1258 |
"speakers": 11000000,
|
1259 |
+
"bleu": 55.46880910094653,
|
1260 |
+
"bert_score": 0.9008744815985362
|
1261 |
},
|
1262 |
{
|
1263 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1265 |
"target_language": "kik_Latn",
|
1266 |
"target_language_name": "Gikuyu",
|
1267 |
"speakers": 6623000,
|
1268 |
+
"bleu": 40.92882752909001,
|
1269 |
+
"bert_score": 0.8850945432980856
|
1270 |
},
|
1271 |
{
|
1272 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1274 |
"target_language": "tso_Latn",
|
1275 |
"target_language_name": "Tsonga",
|
1276 |
"speakers": 13000000,
|
1277 |
+
"bleu": 58.35165735971044,
|
1278 |
+
"bert_score": 0.9134832978248596
|
1279 |
},
|
1280 |
{
|
1281 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1283 |
"target_language": "tat_Cyrl",
|
1284 |
"target_language_name": "Tatar",
|
1285 |
"speakers": 5427318,
|
1286 |
+
"bleu": 60.3447467212788,
|
1287 |
+
"bert_score": 0.9364115715026855
|
1288 |
},
|
1289 |
{
|
1290 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1292 |
"target_language": "awa_Deva",
|
1293 |
"target_language_name": "Awadhi",
|
1294 |
"speakers": 22000000,
|
1295 |
+
"bleu": 46.0797144146192,
|
1296 |
+
"bert_score": 0.9333642820517222
|
1297 |
},
|
1298 |
{
|
1299 |
"model": "anthropic/claude-3.5-sonnet",
|
1300 |
"original_language": "eng_Latn",
|
1301 |
"target_language": "gom_Deva",
|
1302 |
+
"target_language_name": "Goan Konkani",
|
1303 |
"speakers": 3633900,
|
1304 |
+
"bleu": 47.108401794496295,
|
1305 |
+
"bert_score": 0.931428724527359
|
1306 |
},
|
1307 |
{
|
1308 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1310 |
"target_language": "amh_Ethi",
|
1311 |
"target_language_name": "Amharic",
|
1312 |
"speakers": 25000000,
|
1313 |
+
"bleu": 43.15445686971015,
|
1314 |
+
"bert_score": 0.9891169210275014
|
1315 |
},
|
1316 |
{
|
1317 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1319 |
"target_language": "tam_Taml",
|
1320 |
"target_language_name": "Tamil",
|
1321 |
"speakers": 75000000,
|
1322 |
+
"bleu": 65.78632210538115,
|
1323 |
+
"bert_score": 0.9536473691463471
|
1324 |
},
|
1325 |
{
|
1326 |
"model": "openai/gpt-4o-mini",
|
|
|
1328 |
"target_language": "isl_Latn",
|
1329 |
"target_language_name": "Icelandic",
|
1330 |
"speakers": 358000,
|
1331 |
+
"bleu": 61.13552606922321,
|
1332 |
+
"bert_score": 0.9258354703585306
|
1333 |
},
|
1334 |
{
|
1335 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1337 |
"target_language": "isl_Latn",
|
1338 |
"target_language_name": "Icelandic",
|
1339 |
"speakers": 358000,
|
1340 |
+
"bleu": 66.67473000551618,
|
1341 |
+
"bert_score": 0.938145500421524
|
1342 |
},
|
1343 |
{
|
1344 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
|
|
1346 |
"target_language": "isl_Latn",
|
1347 |
"target_language_name": "Icelandic",
|
1348 |
"speakers": 358000,
|
1349 |
+
"bleu": 58.60923195347865,
|
1350 |
+
"bert_score": 0.9203641970952352
|
1351 |
},
|
1352 |
{
|
1353 |
"model": "mistralai/mistral-nemo",
|
|
|
1355 |
"target_language": "isl_Latn",
|
1356 |
"target_language_name": "Icelandic",
|
1357 |
"speakers": 358000,
|
1358 |
+
"bleu": 45.58482442810681,
|
1359 |
+
"bert_score": 0.8916285157203674
|
1360 |
},
|
1361 |
{
|
1362 |
"model": "qwen/qwen-2.5-72b-instruct",
|
|
|
1364 |
"target_language": "isl_Latn",
|
1365 |
"target_language_name": "Icelandic",
|
1366 |
"speakers": 358000,
|
1367 |
+
"bleu": 40.16071522003955,
|
1368 |
+
"bert_score": 0.8842564543088277
|
1369 |
},
|
1370 |
{
|
1371 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1373 |
"target_language": "san_Deva",
|
1374 |
"target_language_name": "Sanskrit",
|
1375 |
"speakers": 49736,
|
1376 |
+
"bleu": 32.78132499113236,
|
1377 |
+
"bert_score": 0.8987655500570934
|
1378 |
},
|
1379 |
{
|
1380 |
"model": "anthropic/claude-3.5-sonnet",
|
1381 |
"original_language": "eng_Latn",
|
1382 |
"target_language": "als_Latn",
|
1383 |
+
"target_language_name": "Tosk Albanian",
|
1384 |
"speakers": 3000000,
|
1385 |
+
"bleu": 69.4218765092482,
|
1386 |
+
"bert_score": 0.940268095334371
|
1387 |
},
|
1388 |
{
|
1389 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1391 |
"target_language": "ron_Latn",
|
1392 |
"target_language_name": "Romanian",
|
1393 |
"speakers": 24300000,
|
1394 |
+
"bleu": 76.4907159034647,
|
1395 |
+
"bert_score": 0.9455295324325561
|
1396 |
},
|
1397 |
{
|
1398 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1400 |
"target_language": "kaz_Cyrl",
|
1401 |
"target_language_name": "Kazakh",
|
1402 |
"speakers": 13161980,
|
1403 |
+
"bleu": 61.12516213751114,
|
1404 |
+
"bert_score": 0.9379647115866343
|
1405 |
},
|
1406 |
{
|
1407 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1409 |
"target_language": "sat_Olck",
|
1410 |
"target_language_name": "Santhali",
|
1411 |
"speakers": 7200000,
|
1412 |
+
"bleu": 31.51192472690372,
|
1413 |
+
"bert_score": 0.9440957049528758
|
1414 |
},
|
1415 |
{
|
1416 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1418 |
"target_language": "ukr_Cyrl",
|
1419 |
"target_language_name": "Ukrainian",
|
1420 |
"speakers": 34710100,
|
1421 |
+
"bleu": 68.09762325436868,
|
1422 |
+
"bert_score": 0.9468558847904205
|
1423 |
},
|
1424 |
{
|
1425 |
"model": "anthropic/claude-3.5-sonnet",
|
1426 |
"original_language": "eng_Latn",
|
1427 |
"target_language": "khk_Cyrl",
|
1428 |
+
"target_language_name": "Halh Mongolian",
|
1429 |
"speakers": 2704030,
|
1430 |
+
"bleu": 58.50377899708198,
|
1431 |
+
"bert_score": 0.9380823055903117
|
1432 |
},
|
1433 |
{
|
1434 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1436 |
"target_language": "bjn_Latn",
|
1437 |
"target_language_name": "Banjar",
|
1438 |
"speakers": 3500000,
|
1439 |
+
"bleu": 56.309519555010915,
|
1440 |
+
"bert_score": 0.901931474606196
|
1441 |
},
|
1442 |
{
|
1443 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1445 |
"target_language": "fon_Latn",
|
1446 |
"target_language_name": "Fon",
|
1447 |
"speakers": 1935500,
|
1448 |
+
"bleu": 25.279777366609945,
|
1449 |
+
"bert_score": 0.8664443592230479
|
1450 |
},
|
1451 |
{
|
1452 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1454 |
"target_language": "sin_Sinh",
|
1455 |
"target_language_name": "Sinhala",
|
1456 |
"speakers": 15300000,
|
1457 |
+
"bleu": 56.75673117959971,
|
1458 |
+
"bert_score": 0.9713358581066132
|
1459 |
},
|
1460 |
{
|
1461 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1463 |
"target_language": "nno_Latn",
|
1464 |
"target_language_name": "nno",
|
1465 |
"speakers": 0,
|
1466 |
+
"bleu": 71.86156462958435,
|
1467 |
+
"bert_score": 0.9335320313771566
|
1468 |
},
|
1469 |
{
|
1470 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1472 |
"target_language": "hau_Latn",
|
1473 |
"target_language_name": "Hausa",
|
1474 |
"speakers": 43900000,
|
1475 |
+
"bleu": 56.34319579006431,
|
1476 |
+
"bert_score": 0.9012877802054088
|
1477 |
},
|
1478 |
{
|
1479 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1481 |
"target_language": "prs_Arab",
|
1482 |
"target_language_name": "Dari",
|
1483 |
"speakers": 9600000,
|
1484 |
+
"bleu": 52.55397957953147,
|
1485 |
+
"bert_score": 0.9466466506322225
|
1486 |
},
|
1487 |
{
|
1488 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1490 |
"target_language": "ell_Grek",
|
1491 |
"target_language_name": "Greek",
|
1492 |
"speakers": 15000000,
|
1493 |
+
"bleu": 66.23477821529342,
|
1494 |
+
"bert_score": 0.9577525118986766
|
1495 |
},
|
1496 |
{
|
1497 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1499 |
"target_language": "tpi_Latn",
|
1500 |
"target_language_name": "Tok Pisin",
|
1501 |
"speakers": 4000000,
|
1502 |
+
"bleu": 56.54077603673191,
|
1503 |
+
"bert_score": 0.903118242820104
|
1504 |
},
|
1505 |
{
|
1506 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1508 |
"target_language": "hye_Armn",
|
1509 |
"target_language_name": "Armenian",
|
1510 |
"speakers": 6700000,
|
1511 |
+
"bleu": 64.68044008058686,
|
1512 |
+
"bert_score": 0.9550812800725301
|
1513 |
},
|
1514 |
{
|
1515 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1517 |
"target_language": "eus_Latn",
|
1518 |
"target_language_name": "Basque",
|
1519 |
"speakers": 750000,
|
1520 |
+
"bleu": 65.89687213771296,
|
1521 |
+
"bert_score": 0.9192741294701894
|
1522 |
},
|
1523 |
{
|
1524 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1526 |
"target_language": "nob_Latn",
|
1527 |
"target_language_name": "Bokmål",
|
1528 |
"speakers": 4000000,
|
1529 |
+
"bleu": 77.49395130155645,
|
1530 |
+
"bert_score": 0.9550971885522207
|
1531 |
},
|
1532 |
{
|
1533 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1535 |
"target_language": "slk_Latn",
|
1536 |
"target_language_name": "Slovak",
|
1537 |
"speakers": 6000000,
|
1538 |
+
"bleu": 67.92848040860814,
|
1539 |
+
"bert_score": 0.9360236605008443
|
1540 |
},
|
1541 |
{
|
1542 |
"model": "anthropic/claude-3.5-sonnet",
|
1543 |
"original_language": "eng_Latn",
|
1544 |
"target_language": "knc_Arab",
|
1545 |
+
"target_language_name": "Yerwa Kanuri",
|
1546 |
"speakers": 0,
|
1547 |
+
"bleu": 14.954246536984446,
|
1548 |
+
"bert_score": 0.8674997230370839
|
1549 |
},
|
1550 |
{
|
1551 |
"model": "openai/gpt-4o-mini",
|
|
|
1553 |
"target_language": "lin_Latn",
|
1554 |
"target_language_name": "Lingala",
|
1555 |
"speakers": 20000000,
|
1556 |
+
"bleu": 50.384710146677506,
|
1557 |
+
"bert_score": 0.887447464466095
|
1558 |
},
|
1559 |
{
|
1560 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1562 |
"target_language": "lin_Latn",
|
1563 |
"target_language_name": "Lingala",
|
1564 |
"speakers": 20000000,
|
1565 |
+
"bleu": 56.735518064625495,
|
1566 |
+
"bert_score": 0.900246125459671
|
1567 |
},
|
1568 |
{
|
1569 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
|
|
1571 |
"target_language": "lin_Latn",
|
1572 |
"target_language_name": "Lingala",
|
1573 |
"speakers": 20000000,
|
1574 |
+
"bleu": 19.732953348932526,
|
1575 |
+
"bert_score": 0.8526991029580434
|
1576 |
},
|
1577 |
{
|
1578 |
"model": "mistralai/mistral-nemo",
|
|
|
1580 |
"target_language": "lin_Latn",
|
1581 |
"target_language_name": "Lingala",
|
1582 |
"speakers": 20000000,
|
1583 |
+
"bleu": 8.64985622273109,
|
1584 |
+
"bert_score": 0.8075945158799489
|
1585 |
},
|
1586 |
{
|
1587 |
"model": "qwen/qwen-2.5-72b-instruct",
|
|
|
1589 |
"target_language": "lin_Latn",
|
1590 |
"target_language_name": "Lingala",
|
1591 |
"speakers": 20000000,
|
1592 |
+
"bleu": 16.658410482633357,
|
1593 |
+
"bert_score": 0.8286310772101084
|
1594 |
},
|
1595 |
{
|
1596 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1598 |
"target_language": "bam_Latn",
|
1599 |
"target_language_name": "Bamanankan",
|
1600 |
"speakers": 2700000,
|
1601 |
+
"bleu": 38.693909140769804,
|
1602 |
+
"bert_score": 0.887204376856486
|
1603 |
},
|
1604 |
{
|
1605 |
"model": "anthropic/claude-3.5-sonnet",
|
1606 |
"original_language": "eng_Latn",
|
1607 |
"target_language": "sot_Latn",
|
1608 |
+
"target_language_name": "Southern Sotho",
|
1609 |
"speakers": 6000000,
|
1610 |
+
"bleu": 56.73529955399566,
|
1611 |
+
"bert_score": 0.9102749407291413
|
1612 |
},
|
1613 |
{
|
1614 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1616 |
"target_language": "min_Arab",
|
1617 |
"target_language_name": "Minangkabau",
|
1618 |
"speakers": 5530000,
|
1619 |
+
"bleu": 37.44925084737469,
|
1620 |
+
"bert_score": 0.9340883692105612
|
1621 |
},
|
1622 |
{
|
1623 |
"model": "anthropic/claude-3.5-sonnet",
|
1624 |
"original_language": "eng_Latn",
|
1625 |
"target_language": "zgh_Tfng",
|
1626 |
+
"target_language_name": "Standard Moroccan Tamazight",
|
1627 |
"speakers": 0,
|
1628 |
+
"bleu": 35.62476481092257,
|
1629 |
+
"bert_score": 0.9847298423449199
|
1630 |
},
|
1631 |
{
|
1632 |
"model": "anthropic/claude-3.5-sonnet",
|
1633 |
"original_language": "eng_Latn",
|
1634 |
"target_language": "gug_Latn",
|
1635 |
+
"target_language_name": "Paraguayan Guaraní",
|
1636 |
"speakers": 0,
|
1637 |
+
"bleu": 41.79298637071421,
|
1638 |
+
"bert_score": 0.8764786461989085
|
1639 |
},
|
1640 |
{
|
1641 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1643 |
"target_language": "lmo_Latn",
|
1644 |
"target_language_name": "Lombard",
|
1645 |
"speakers": 3900000,
|
1646 |
+
"bleu": 46.38844026736926,
|
1647 |
+
"bert_score": 0.8643471499284109
|
1648 |
},
|
1649 |
{
|
1650 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1652 |
"target_language": "yor_Latn",
|
1653 |
"target_language_name": "Yoruba",
|
1654 |
"speakers": 40000000,
|
1655 |
+
"bleu": 34.264254226792296,
|
1656 |
+
"bert_score": 0.9001545011997223
|
1657 |
},
|
1658 |
{
|
1659 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1661 |
"target_language": "taq_Tfng",
|
1662 |
"target_language_name": "Tamasheq",
|
1663 |
"speakers": 500000,
|
1664 |
+
"bleu": 10.997033033155907,
|
1665 |
+
"bert_score": 0.8574198484420776
|
1666 |
},
|
1667 |
{
|
1668 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1670 |
"target_language": "tgk_Cyrl",
|
1671 |
"target_language_name": "Tajik",
|
1672 |
"speakers": 14000000,
|
1673 |
+
"bleu": 60.97836841576954,
|
1674 |
+
"bert_score": 0.9378365337848663
|
1675 |
},
|
1676 |
{
|
1677 |
"model": "anthropic/claude-3.5-sonnet",
|
1678 |
"original_language": "eng_Latn",
|
1679 |
"target_language": "fuv_Latn",
|
1680 |
+
"target_language_name": "Nigerian Fulfulde",
|
1681 |
"speakers": 14500000,
|
1682 |
+
"bleu": 28.17610559128895,
|
1683 |
+
"bert_score": 0.8343587597211202
|
1684 |
},
|
1685 |
{
|
1686 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1688 |
"target_language": "mal_Mlym",
|
1689 |
"target_language_name": "Malayalam",
|
1690 |
"speakers": 37100000,
|
1691 |
+
"bleu": 64.06558940908465,
|
1692 |
+
"bert_score": 0.9803075671195984
|
1693 |
},
|
1694 |
{
|
1695 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1697 |
"target_language": "tel_Telu",
|
1698 |
"target_language_name": "Telugu",
|
1699 |
"speakers": 82000000,
|
1700 |
+
"bleu": 61.635245762892694,
|
1701 |
+
"bert_score": 0.9790697515010833
|
1702 |
},
|
1703 |
{
|
1704 |
"model": "anthropic/claude-3.5-sonnet",
|
1705 |
"original_language": "eng_Latn",
|
1706 |
"target_language": "arb_Arab",
|
1707 |
+
"target_language_name": "Standard Arabic",
|
1708 |
"speakers": 0,
|
1709 |
+
"bleu": 65.04139779040646,
|
1710 |
+
"bert_score": 0.9535989860693613
|
1711 |
},
|
1712 |
{
|
1713 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1715 |
"target_language": "khm_Khmr",
|
1716 |
"target_language_name": "Khmer",
|
1717 |
"speakers": 16600000,
|
1718 |
+
"bleu": 49.209825704340375,
|
1719 |
+
"bert_score": 0.8907732884089152
|
1720 |
},
|
1721 |
{
|
1722 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1724 |
"target_language": "scn_Latn",
|
1725 |
"target_language_name": "Sicilian",
|
1726 |
"speakers": 4700000,
|
1727 |
+
"bleu": 58.589535944250635,
|
1728 |
+
"bert_score": 0.9042834500471751
|
1729 |
},
|
1730 |
{
|
1731 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1733 |
"target_language": "ltz_Latn",
|
1734 |
"target_language_name": "Luxembourgish",
|
1735 |
"speakers": 391200,
|
1736 |
+
"bleu": 70.8338190437548,
|
1737 |
+
"bert_score": 0.9297492106755575
|
1738 |
},
|
1739 |
{
|
1740 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1742 |
"target_language": "pag_Latn",
|
1743 |
"target_language_name": "Pangasinan",
|
1744 |
"speakers": 1100000,
|
1745 |
+
"bleu": 56.00481838266269,
|
1746 |
+
"bert_score": 0.890628065665563
|
1747 |
},
|
1748 |
{
|
1749 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1751 |
"target_language": "kab_Latn",
|
1752 |
"target_language_name": "Kabyle",
|
1753 |
"speakers": 5586000,
|
1754 |
+
"bleu": 41.14429925869902,
|
1755 |
+
"bert_score": 0.8803219795227051
|
1756 |
},
|
1757 |
{
|
1758 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1760 |
"target_language": "bak_Cyrl",
|
1761 |
"target_language_name": "Bashkort",
|
1762 |
"speakers": 1200000,
|
1763 |
+
"bleu": 57.54538429274717,
|
1764 |
+
"bert_score": 0.9298217594623566
|
1765 |
},
|
1766 |
{
|
1767 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1769 |
"target_language": "twi_Latn_akua1239",
|
1770 |
"target_language_name": "Twi",
|
1771 |
"speakers": 3000000,
|
1772 |
+
"bleu": 45.1519376004116,
|
1773 |
+
"bert_score": 0.8945407330989837
|
1774 |
},
|
1775 |
{
|
1776 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1778 |
"target_language": "hin_Deva",
|
1779 |
"target_language_name": "Hindi",
|
1780 |
"speakers": 341000000,
|
1781 |
+
"bleu": 64.936216689785,
|
1782 |
+
"bert_score": 0.9463364283243815
|
1783 |
},
|
1784 |
{
|
1785 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1787 |
"target_language": "kas_Arab",
|
1788 |
"target_language_name": "Kashmiri",
|
1789 |
"speakers": 6900000,
|
1790 |
+
"bleu": 38.28328065553461,
|
1791 |
+
"bert_score": 0.9321333905061086
|
1792 |
},
|
1793 |
{
|
1794 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1796 |
"target_language": "mlt_Latn",
|
1797 |
"target_language_name": "Maltese",
|
1798 |
"speakers": 570000,
|
1799 |
+
"bleu": 80.08667772627608,
|
1800 |
+
"bert_score": 0.9520254651705424
|
1801 |
},
|
1802 |
{
|
1803 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1805 |
"target_language": "som_Latn",
|
1806 |
"target_language_name": "Somali",
|
1807 |
"speakers": 16200000,
|
1808 |
+
"bleu": 55.370649647294535,
|
1809 |
+
"bert_score": 0.9085715929667155
|
1810 |
},
|
1811 |
{
|
1812 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1814 |
"target_language": "hne_Deva",
|
1815 |
"target_language_name": "Chhattisgarhi",
|
1816 |
"speakers": 16300000,
|
1817 |
+
"bleu": 47.979750130407254,
|
1818 |
+
"bert_score": 0.9363766014575958
|
1819 |
},
|
1820 |
{
|
1821 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1823 |
"target_language": "glg_Latn",
|
1824 |
"target_language_name": "Galician",
|
1825 |
"speakers": 2500000,
|
1826 |
+
"bleu": 68.70247869041181,
|
1827 |
+
"bert_score": 0.9283550182978312
|
1828 |
},
|
1829 |
{
|
1830 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1832 |
"target_language": "ory_Orya",
|
1833 |
"target_language_name": "Odia",
|
1834 |
"speakers": 34500000,
|
1835 |
+
"bleu": 57.362809651798656,
|
1836 |
+
"bert_score": 0.9768644154071808
|
1837 |
},
|
1838 |
{
|
1839 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1841 |
"target_language": "nld_Latn",
|
1842 |
"target_language_name": "Dutch",
|
1843 |
"speakers": 23100000,
|
1844 |
+
"bleu": 71.18493263152928,
|
1845 |
+
"bert_score": 0.9376831948757172
|
1846 |
},
|
1847 |
{
|
1848 |
"model": "anthropic/claude-3.5-sonnet",
|
1849 |
"original_language": "eng_Latn",
|
1850 |
"target_language": "apc_Arab_sout3123",
|
1851 |
+
"target_language_name": "Levantine Arabic",
|
1852 |
"speakers": 44000000,
|
1853 |
+
"bleu": 56.235711236638,
|
1854 |
+
"bert_score": 0.9452390710512797
|
1855 |
},
|
1856 |
{
|
1857 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1859 |
"target_language": "oci_Latn",
|
1860 |
"target_language_name": "Occitan",
|
1861 |
"speakers": 542000,
|
1862 |
+
"bleu": 71.53274018395614,
|
1863 |
+
"bert_score": 0.9337525626023611
|
1864 |
},
|
1865 |
{
|
1866 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1868 |
"target_language": "mni_Beng",
|
1869 |
"target_language_name": "Meitei",
|
1870 |
"speakers": 1470000,
|
1871 |
+
"bleu": 40.61648039338993,
|
1872 |
+
"bert_score": 0.9325185577074687
|
1873 |
},
|
1874 |
{
|
1875 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1877 |
"target_language": "hun_Latn",
|
1878 |
"target_language_name": "Hungarian",
|
1879 |
"speakers": 12600000,
|
1880 |
+
"bleu": 66.13011194084116,
|
1881 |
+
"bert_score": 0.924921864271164
|
1882 |
},
|
1883 |
{
|
1884 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1886 |
"target_language": "bho_Deva",
|
1887 |
"target_language_name": "Bhojpuri",
|
1888 |
"speakers": 52200000,
|
1889 |
+
"bleu": 44.54123379070156,
|
1890 |
+
"bert_score": 0.9288184980551402
|
1891 |
},
|
1892 |
{
|
1893 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1895 |
"target_language": "mya_Mymr",
|
1896 |
"target_language_name": "Burmese",
|
1897 |
"speakers": 32900000,
|
1898 |
+
"bleu": 55.723591167735165,
|
1899 |
+
"bert_score": 0.975975106159846
|
1900 |
},
|
1901 |
{
|
1902 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1904 |
"target_language": "run_Latn",
|
1905 |
"target_language_name": "Rundi",
|
1906 |
"speakers": 10800000,
|
1907 |
+
"bleu": 48.94351362900039,
|
1908 |
+
"bert_score": 0.8933652222156525
|
1909 |
},
|
1910 |
{
|
1911 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1913 |
"target_language": "ast_Latn",
|
1914 |
"target_language_name": "Asturian",
|
1915 |
"speakers": 450000,
|
1916 |
+
"bleu": 71.34456234933488,
|
1917 |
+
"bert_score": 0.931475841999054
|
1918 |
},
|
1919 |
{
|
1920 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1922 |
"target_language": "tir_Ethi",
|
1923 |
"target_language_name": "Tigrigna",
|
1924 |
"speakers": 7507780,
|
1925 |
+
"bleu": 32.87119617033141,
|
1926 |
+
"bert_score": 0.9852415164311726
|
1927 |
},
|
1928 |
{
|
1929 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1931 |
"target_language": "kac_Latn",
|
1932 |
"target_language_name": "Jingpho",
|
1933 |
"speakers": 940000,
|
1934 |
+
"bleu": 43.550058140290794,
|
1935 |
+
"bert_score": 0.8727998991807302
|
1936 |
},
|
1937 |
{
|
1938 |
"model": "anthropic/claude-3.5-sonnet",
|
1939 |
"original_language": "eng_Latn",
|
1940 |
"target_language": "acm_Arab",
|
1941 |
+
"target_language_name": "Mesopotamian Arabic",
|
1942 |
"speakers": 15700000,
|
1943 |
+
"bleu": 49.51848652969806,
|
1944 |
+
"bert_score": 0.9382626354694367
|
1945 |
},
|
1946 |
{
|
1947 |
"model": "anthropic/claude-3.5-sonnet",
|
1948 |
"original_language": "eng_Latn",
|
1949 |
"target_language": "arz_Arab",
|
1950 |
+
"target_language_name": "Egyptian Arabic",
|
1951 |
"speakers": 100542400,
|
1952 |
+
"bleu": 53.68180810376352,
|
1953 |
+
"bert_score": 0.9394114673137665
|
1954 |
},
|
1955 |
{
|
1956 |
"model": "anthropic/claude-3.5-sonnet",
|
1957 |
"original_language": "eng_Latn",
|
1958 |
"target_language": "mhr_Cyrl",
|
1959 |
+
"target_language_name": "Meadow Mari",
|
1960 |
"speakers": 482000,
|
1961 |
+
"bleu": 49.791168058232124,
|
1962 |
+
"bert_score": 0.929511696100235
|
1963 |
},
|
1964 |
{
|
1965 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1967 |
"target_language": "ita_Latn",
|
1968 |
"target_language_name": "Italian",
|
1969 |
"speakers": 64819790,
|
1970 |
+
"bleu": 69.15883435724486,
|
1971 |
+
"bert_score": 0.9358606537183126
|
1972 |
},
|
1973 |
{
|
1974 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
1976 |
"target_language": "spa_Latn",
|
1977 |
"target_language_name": "Spanish",
|
1978 |
"speakers": 485000000,
|
1979 |
+
"bleu": 63.84670733785411,
|
1980 |
+
"bert_score": 0.922440630197525
|
1981 |
},
|
1982 |
{
|
1983 |
"model": "anthropic/claude-3.5-sonnet",
|
1984 |
"original_language": "eng_Latn",
|
1985 |
"target_language": "ydd_Hebr",
|
1986 |
+
"target_language_name": "Eastern Yiddish",
|
1987 |
"speakers": 0,
|
1988 |
+
"bleu": 47.55620093253461,
|
1989 |
+
"bert_score": 0.9590989410877228
|
1990 |
},
|
1991 |
{
|
1992 |
"model": "anthropic/claude-3.5-sonnet",
|
1993 |
"original_language": "eng_Latn",
|
1994 |
"target_language": "gaz_Latn",
|
1995 |
+
"target_language_name": "West Central Oromo",
|
1996 |
"speakers": 0,
|
1997 |
+
"bleu": 46.909035002775134,
|
1998 |
+
"bert_score": 0.8845542371273041
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"model": "anthropic/claude-3.5-sonnet",
|
2002 |
+
"original_language": "eng_Latn",
|
2003 |
+
"target_language": "eng_Latn",
|
2004 |
+
"target_language_name": "English",
|
2005 |
+
"speakers": 1132366680,
|
2006 |
+
"bleu": 75.35011734860745,
|
2007 |
+
"bert_score": 0.880733436346054
|
2008 |
},
|
2009 |
{
|
2010 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
2012 |
"target_language": "ktu_Latn",
|
2013 |
"target_language_name": "Kituba (Democratic Republic of the Congo)",
|
2014 |
"speakers": 0,
|
2015 |
+
"bleu": 52.848460160201476,
|
2016 |
+
"bert_score": 0.9017938395341237
|
2017 |
},
|
2018 |
{
|
2019 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
2021 |
"target_language": "dyu_Latn",
|
2022 |
"target_language_name": "Jula",
|
2023 |
"speakers": 2700000,
|
2024 |
+
"bleu": 29.541518029704612,
|
2025 |
+
"bert_score": 0.8223321119944255
|
2026 |
},
|
2027 |
{
|
2028 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
2030 |
"target_language": "ace_Latn",
|
2031 |
"target_language_name": "Aceh",
|
2032 |
"speakers": 3500032,
|
2033 |
+
"bleu": 54.98266447488466,
|
2034 |
+
"bert_score": 0.9054659227530162
|
2035 |
},
|
2036 |
{
|
2037 |
"model": "anthropic/claude-3.5-sonnet",
|
2038 |
"original_language": "eng_Latn",
|
2039 |
"target_language": "ckb_Arab",
|
2040 |
+
"target_language_name": "Central Kurdish",
|
2041 |
"speakers": 7250000,
|
2042 |
+
"bleu": 59.19279106924606,
|
2043 |
+
"bert_score": 0.933256882429123
|
2044 |
},
|
2045 |
{
|
2046 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
2048 |
"target_language": "mos_Latn",
|
2049 |
"target_language_name": "Moore",
|
2050 |
"speakers": 7600000,
|
2051 |
+
"bleu": 32.845809798291015,
|
2052 |
+
"bert_score": 0.8583020627498626
|
2053 |
},
|
2054 |
{
|
2055 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
2057 |
"target_language": "kir_Cyrl",
|
2058 |
"target_language_name": "Kyrgyz",
|
2059 |
"speakers": 4568480,
|
2060 |
+
"bleu": 57.082442245268965,
|
2061 |
+
"bert_score": 0.9317750076452891
|
2062 |
},
|
2063 |
{
|
2064 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
2066 |
"target_language": "npi_Deva",
|
2067 |
"target_language_name": "Nepali",
|
2068 |
"speakers": 0,
|
2069 |
+
"bleu": 55.29193473519464,
|
2070 |
+
"bert_score": 0.9358912428220113
|
2071 |
},
|
2072 |
{
|
2073 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
2075 |
"target_language": "kbp_Latn",
|
2076 |
"target_language_name": "Kabiyè",
|
2077 |
"speakers": 1000000,
|
2078 |
+
"bleu": 22.549850465519835,
|
2079 |
+
"bert_score": 0.8587520639101665
|
2080 |
},
|
2081 |
{
|
2082 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
2084 |
"target_language": "bem_Latn",
|
2085 |
"target_language_name": "Bemba",
|
2086 |
"speakers": 3600000,
|
2087 |
+
"bleu": 47.80685489558032,
|
2088 |
+
"bert_score": 0.889907830953598
|
2089 |
}
|
2090 |
]
|
results_summary.json
CHANGED
@@ -1,997 +1,1202 @@
|
|
1 |
[
|
2 |
-
{
|
3 |
-
"target_language_name":" Ayacucho Quechua",
|
4 |
-
"bleu":46.244412926,
|
5 |
-
"speakers":918200.0
|
6 |
-
},
|
7 |
-
{
|
8 |
-
"target_language_name":" Central Aymara",
|
9 |
-
"bleu":40.7737907059,
|
10 |
-
"speakers":0.0
|
11 |
-
},
|
12 |
-
{
|
13 |
-
"target_language_name":" Central Kurdish",
|
14 |
-
"bleu":58.3049111733,
|
15 |
-
"speakers":7250000.0
|
16 |
-
},
|
17 |
-
{
|
18 |
-
"target_language_name":" Central Tibetan",
|
19 |
-
"bleu":51.762059856,
|
20 |
-
"speakers":1200000.0
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"target_language_name":" Eastern Punjabi",
|
24 |
-
"bleu":60.8335398677,
|
25 |
-
"speakers":125000000.0
|
26 |
-
},
|
27 |
-
{
|
28 |
-
"target_language_name":" Eastern Yiddish",
|
29 |
-
"bleu":49.9745007585,
|
30 |
-
"speakers":0.0
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"target_language_name":" Egyptian Arabic",
|
34 |
-
"bleu":54.068278052,
|
35 |
-
"speakers":100542400.0
|
36 |
-
},
|
37 |
-
{
|
38 |
-
"target_language_name":" Goan Konkani",
|
39 |
-
"bleu":46.8883507968,
|
40 |
-
"speakers":3633900.0
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"target_language_name":" Halh Mongolian",
|
44 |
-
"bleu":59.1426397299,
|
45 |
-
"speakers":2704030.0
|
46 |
-
},
|
47 |
-
{
|
48 |
-
"target_language_name":" Iranian Persian",
|
49 |
-
"bleu":57.466690672,
|
50 |
-
"speakers":52800000.0
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"target_language_name":" Levantine Arabic",
|
54 |
-
"bleu":56.1658711447,
|
55 |
-
"speakers":44000000.0
|
56 |
-
},
|
57 |
-
{
|
58 |
-
"target_language_name":" Mandarin Chinese",
|
59 |
-
"bleu":42.5923366202,
|
60 |
-
"speakers":1074000000.0
|
61 |
-
},
|
62 |
-
{
|
63 |
-
"target_language_name":" Meadow Mari",
|
64 |
-
"bleu":49.5606117273,
|
65 |
-
"speakers":482000.0
|
66 |
-
},
|
67 |
-
{
|
68 |
-
"target_language_name":" Merina Malagasy",
|
69 |
-
"bleu":60.4304388047,
|
70 |
-
"speakers":0.0
|
71 |
-
},
|
72 |
-
{
|
73 |
-
"target_language_name":" Mesopotamian Arabic",
|
74 |
-
"bleu":50.0865634269,
|
75 |
-
"speakers":15700000.0
|
76 |
-
},
|
77 |
-
{
|
78 |
-
"target_language_name":" Moroccan Arabic",
|
79 |
-
"bleu":48.5607873978,
|
80 |
-
"speakers":27500000.0
|
81 |
-
},
|
82 |
-
{
|
83 |
-
"target_language_name":" Najdi Arabic",
|
84 |
-
"bleu":47.7692581451,
|
85 |
-
"speakers":0.0
|
86 |
-
},
|
87 |
-
{
|
88 |
-
"target_language_name":" Nigerian Fulfulde",
|
89 |
-
"bleu":28.2458571831,
|
90 |
-
"speakers":14500000.0
|
91 |
-
},
|
92 |
-
{
|
93 |
-
"target_language_name":" North Azerbaijani",
|
94 |
-
"bleu":55.0045961351,
|
95 |
-
"speakers":9220610.0
|
96 |
-
},
|
97 |
-
{
|
98 |
-
"target_language_name":" Northern Kurdish",
|
99 |
-
"bleu":55.0085600267,
|
100 |
-
"speakers":14600000.0
|
101 |
-
},
|
102 |
-
{
|
103 |
-
"target_language_name":" Northern Sotho",
|
104 |
-
"bleu":63.0482508066,
|
105 |
-
"speakers":4100000.0
|
106 |
-
},
|
107 |
-
{
|
108 |
-
"target_language_name":" Northern Uzbek",
|
109 |
-
"bleu":64.07804482,
|
110 |
-
"speakers":26912410.0
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"target_language_name":" Paraguayan Guaran\u00ed",
|
114 |
-
"bleu":42.9023503897,
|
115 |
-
"speakers":0.0
|
116 |
-
},
|
117 |
-
{
|
118 |
-
"target_language_name":" South Azerbaijani",
|
119 |
-
"bleu":43.5362266708,
|
120 |
-
"speakers":15000000.0
|
121 |
-
},
|
122 |
-
{
|
123 |
-
"target_language_name":" Southern Pashto",
|
124 |
-
"bleu":38.5486962222,
|
125 |
-
"speakers":10900000.0
|
126 |
-
},
|
127 |
-
{
|
128 |
-
"target_language_name":" Southern Sotho",
|
129 |
-
"bleu":57.1537510266,
|
130 |
-
"speakers":6000000.0
|
131 |
-
},
|
132 |
-
{
|
133 |
-
"target_language_name":" Southwestern Dinka",
|
134 |
-
"bleu":12.4978320514,
|
135 |
-
"speakers":0.0
|
136 |
-
},
|
137 |
-
{
|
138 |
-
"target_language_name":" Standard Arabic",
|
139 |
-
"bleu":56.6219786764,
|
140 |
-
"speakers":0.0
|
141 |
-
},
|
142 |
-
{
|
143 |
-
"target_language_name":" Standard Estonian",
|
144 |
-
"bleu":68.0693526943,
|
145 |
-
"speakers":1164770.0
|
146 |
-
},
|
147 |
-
{
|
148 |
-
"target_language_name":" Standard German",
|
149 |
-
"bleu":77.2213038369,
|
150 |
-
"speakers":105000000.0
|
151 |
-
},
|
152 |
-
{
|
153 |
-
"target_language_name":" Standard Latvian",
|
154 |
-
"bleu":64.8995188161,
|
155 |
-
"speakers":0.0
|
156 |
-
},
|
157 |
-
{
|
158 |
-
"target_language_name":" Standard Malay",
|
159 |
-
"bleu":75.5868255696,
|
160 |
-
"speakers":0.0
|
161 |
-
},
|
162 |
-
{
|
163 |
-
"target_language_name":" Standard Moroccan Tamazight",
|
164 |
-
"bleu":36.0211020389,
|
165 |
-
"speakers":0.0
|
166 |
-
},
|
167 |
-
{
|
168 |
-
"target_language_name":" Ta\u2019izzi-Adeni Arabic",
|
169 |
-
"bleu":48.6728574258,
|
170 |
-
"speakers":10500000.0
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"target_language_name":" Tosk Albanian",
|
174 |
-
"bleu":69.2428556015,
|
175 |
-
"speakers":3000000.0
|
176 |
-
},
|
177 |
-
{
|
178 |
-
"target_language_name":" Tunisian Arabic",
|
179 |
-
"bleu":49.8735980011,
|
180 |
-
"speakers":11600000.0
|
181 |
-
},
|
182 |
-
{
|
183 |
-
"target_language_name":" West Central Oromo",
|
184 |
-
"bleu":47.1911435507,
|
185 |
-
"speakers":0.0
|
186 |
-
},
|
187 |
-
{
|
188 |
-
"target_language_name":" Yerwa Kanuri",
|
189 |
-
"bleu":18.4779991227,
|
190 |
-
"speakers":0.0
|
191 |
-
},
|
192 |
-
{
|
193 |
-
"target_language_name":" Yue Chinese",
|
194 |
-
"bleu":34.2560977082,
|
195 |
-
"speakers":73100000.0
|
196 |
-
},
|
197 |
{
|
198 |
"target_language_name":"Aceh",
|
199 |
"bleu":39.1659660901,
|
|
|
200 |
"speakers":3500032.0
|
201 |
},
|
202 |
{
|
203 |
"target_language_name":"Afrikaans",
|
204 |
"bleu":76.8900540777,
|
|
|
205 |
"speakers":10300000.0
|
206 |
},
|
207 |
{
|
208 |
"target_language_name":"Amharic",
|
209 |
"bleu":43.1544568697,
|
|
|
210 |
"speakers":25000000.0
|
211 |
},
|
212 |
{
|
213 |
"target_language_name":"Armenian",
|
214 |
"bleu":64.6804400806,
|
|
|
215 |
"speakers":6700000.0
|
216 |
},
|
217 |
{
|
218 |
"target_language_name":"Assamese",
|
219 |
"bleu":47.0351331605,
|
|
|
220 |
"speakers":15300000.0
|
221 |
},
|
222 |
{
|
223 |
"target_language_name":"Asturian",
|
224 |
"bleu":71.3445623493,
|
|
|
225 |
"speakers":450000.0
|
226 |
},
|
227 |
{
|
228 |
"target_language_name":"Awadhi",
|
229 |
"bleu":46.0797144146,
|
|
|
230 |
"speakers":22000000.0
|
231 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
232 |
{
|
233 |
"target_language_name":"Bali (Indonesia)",
|
234 |
"bleu":52.8752419159,
|
|
|
235 |
"speakers":4000000.0
|
236 |
},
|
237 |
{
|
238 |
"target_language_name":"Bamanankan",
|
239 |
"bleu":38.6939091408,
|
|
|
240 |
"speakers":2700000.0
|
241 |
},
|
242 |
{
|
243 |
"target_language_name":"Banjar",
|
244 |
"bleu":46.5453977487,
|
|
|
245 |
"speakers":3500000.0
|
246 |
},
|
247 |
{
|
248 |
"target_language_name":"Bashkort",
|
249 |
"bleu":57.5453842927,
|
|
|
250 |
"speakers":1200000.0
|
251 |
},
|
252 |
{
|
253 |
"target_language_name":"Basque",
|
254 |
"bleu":65.8968721377,
|
|
|
255 |
"speakers":750000.0
|
256 |
},
|
257 |
{
|
258 |
"target_language_name":"Belarusian",
|
259 |
"bleu":54.5195166442,
|
|
|
260 |
"speakers":7900000.0
|
261 |
},
|
262 |
{
|
263 |
"target_language_name":"Bemba",
|
264 |
"bleu":47.8068548956,
|
|
|
265 |
"speakers":3600000.0
|
266 |
},
|
267 |
{
|
268 |
"target_language_name":"Bengali",
|
269 |
"bleu":57.1417588816,
|
|
|
270 |
"speakers":300000000.0
|
271 |
},
|
272 |
{
|
273 |
"target_language_name":"Bhojpuri",
|
274 |
"bleu":44.5412337907,
|
|
|
275 |
"speakers":52200000.0
|
276 |
},
|
277 |
{
|
278 |
"target_language_name":"Bokm\u00e5l",
|
279 |
"bleu":77.4939513016,
|
|
|
280 |
"speakers":4000000.0
|
281 |
},
|
282 |
{
|
283 |
"target_language_name":"Boro (India)",
|
284 |
"bleu":36.1100474969,
|
|
|
285 |
"speakers":1482929.0
|
286 |
},
|
287 |
{
|
288 |
"target_language_name":"Bosnian",
|
289 |
"bleu":72.5488027131,
|
|
|
290 |
"speakers":3500000.0
|
291 |
},
|
292 |
{
|
293 |
"target_language_name":"Bugis",
|
294 |
"bleu":44.8388170031,
|
|
|
295 |
"speakers":5017800.0
|
296 |
},
|
297 |
{
|
298 |
"target_language_name":"Bulgarian",
|
299 |
"bleu":72.9695925131,
|
|
|
300 |
"speakers":9000000.0
|
301 |
},
|
302 |
{
|
303 |
"target_language_name":"Burmese",
|
304 |
"bleu":55.7235911677,
|
|
|
305 |
"speakers":32900000.0
|
306 |
},
|
307 |
{
|
308 |
"target_language_name":"Catalan",
|
309 |
"bleu":74.4595007932,
|
|
|
310 |
"speakers":5100000.0
|
311 |
},
|
312 |
{
|
313 |
"target_language_name":"Cebuano",
|
314 |
"bleu":69.4557958655,
|
|
|
315 |
"speakers":15900000.0
|
316 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
317 |
{
|
318 |
"target_language_name":"Chhattisgarhi",
|
319 |
"bleu":47.9797501304,
|
|
|
320 |
"speakers":16300000.0
|
321 |
},
|
322 |
{
|
323 |
"target_language_name":"Chichewa",
|
324 |
"bleu":59.7601680161,
|
|
|
325 |
"speakers":12000000.0
|
326 |
},
|
327 |
{
|
328 |
"target_language_name":"Chokwe",
|
329 |
"bleu":10.1864074161,
|
|
|
330 |
"speakers":0.0
|
331 |
},
|
332 |
{
|
333 |
"target_language_name":"Chuvash",
|
334 |
"bleu":45.0546658723,
|
|
|
335 |
"speakers":1279650.0
|
336 |
},
|
337 |
{
|
338 |
"target_language_name":"Crimean Tatar",
|
339 |
"bleu":52.7050249448,
|
|
|
340 |
"speakers":552740.0
|
341 |
},
|
342 |
{
|
343 |
"target_language_name":"Croatian",
|
344 |
"bleu":69.5456983662,
|
|
|
345 |
"speakers":7000000.0
|
346 |
},
|
347 |
{
|
348 |
"target_language_name":"Czech",
|
349 |
"bleu":69.7112290599,
|
|
|
350 |
"speakers":10700000.0
|
351 |
},
|
352 |
{
|
353 |
"target_language_name":"Danish",
|
354 |
"bleu":78.0935433284,
|
|
|
355 |
"speakers":6000000.0
|
356 |
},
|
357 |
{
|
358 |
"target_language_name":"Dari",
|
359 |
"bleu":52.5539795795,
|
|
|
360 |
"speakers":9600000.0
|
361 |
},
|
362 |
{
|
363 |
"target_language_name":"Dholuo",
|
364 |
"bleu":46.4119479071,
|
|
|
365 |
"speakers":3000000.0
|
366 |
},
|
367 |
{
|
368 |
"target_language_name":"Dogri",
|
369 |
"bleu":44.9153535278,
|
|
|
370 |
"speakers":2000000.0
|
371 |
},
|
372 |
{
|
373 |
"target_language_name":"Dutch",
|
374 |
"bleu":71.1849326315,
|
|
|
375 |
"speakers":23100000.0
|
376 |
},
|
377 |
{
|
378 |
"target_language_name":"Dzongkha",
|
379 |
"bleu":44.3573814017,
|
|
|
380 |
"speakers":237080.0
|
381 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
382 |
{
|
383 |
"target_language_name":"Esperanto",
|
384 |
"bleu":69.6056577554,
|
|
|
385 |
"speakers":2000000.0
|
386 |
},
|
387 |
{
|
388 |
"target_language_name":"Faroese",
|
389 |
"bleu":65.9147902483,
|
|
|
390 |
"speakers":69150.0
|
391 |
},
|
392 |
{
|
393 |
"target_language_name":"Fijian",
|
394 |
"bleu":58.2892667246,
|
|
|
395 |
"speakers":341270.0
|
396 |
},
|
397 |
{
|
398 |
"target_language_name":"Filipino",
|
399 |
"bleu":70.1928498378,
|
|
|
400 |
"speakers":90000000.0
|
401 |
},
|
402 |
{
|
403 |
"target_language_name":"Finnish",
|
404 |
"bleu":70.9425029518,
|
|
|
405 |
"speakers":5413380.0
|
406 |
},
|
407 |
{
|
408 |
"target_language_name":"Fon",
|
409 |
"bleu":25.2797773666,
|
|
|
410 |
"speakers":1935500.0
|
411 |
},
|
412 |
{
|
413 |
"target_language_name":"French",
|
414 |
"bleu":79.3023871219,
|
|
|
415 |
"speakers":208157220.0
|
416 |
},
|
417 |
{
|
418 |
"target_language_name":"Friulian",
|
419 |
"bleu":66.5488092372,
|
|
|
420 |
"speakers":300000.0
|
421 |
},
|
422 |
{
|
423 |
"target_language_name":"Galician",
|
424 |
"bleu":68.7024786904,
|
|
|
425 |
"speakers":2500000.0
|
426 |
},
|
427 |
{
|
428 |
"target_language_name":"Ganda",
|
429 |
"bleu":45.8693322936,
|
|
|
430 |
"speakers":4100000.0
|
431 |
},
|
432 |
{
|
433 |
"target_language_name":"Georgian",
|
434 |
"bleu":61.0166361442,
|
|
|
435 |
"speakers":3700000.0
|
436 |
},
|
437 |
{
|
438 |
"target_language_name":"Gikuyu",
|
439 |
"bleu":40.9288275291,
|
|
|
440 |
"speakers":6623000.0
|
441 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
442 |
{
|
443 |
"target_language_name":"Greek",
|
444 |
"bleu":66.2347782153,
|
|
|
445 |
"speakers":15000000.0
|
446 |
},
|
447 |
{
|
448 |
"target_language_name":"Gujarati",
|
449 |
"bleu":55.5884513452,
|
|
|
450 |
"speakers":56400000.0
|
451 |
},
|
452 |
{
|
453 |
"target_language_name":"Haitian Creole",
|
454 |
"bleu":63.8532187591,
|
|
|
455 |
"speakers":9600000.0
|
456 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
457 |
{
|
458 |
"target_language_name":"Hausa",
|
459 |
"bleu":56.3431957901,
|
|
|
460 |
"speakers":43900000.0
|
461 |
},
|
462 |
{
|
463 |
"target_language_name":"Hebrew",
|
464 |
"bleu":72.0702990513,
|
|
|
465 |
"speakers":9303950.0
|
466 |
},
|
467 |
{
|
468 |
"target_language_name":"Hindi",
|
469 |
"bleu":64.9362166898,
|
|
|
470 |
"speakers":341000000.0
|
471 |
},
|
472 |
{
|
473 |
"target_language_name":"Hungarian",
|
474 |
"bleu":66.1301119408,
|
|
|
475 |
"speakers":12600000.0
|
476 |
},
|
477 |
{
|
478 |
"target_language_name":"Icelandic",
|
479 |
"bleu":54.4330055353,
|
|
|
480 |
"speakers":358000.0
|
481 |
},
|
482 |
{
|
483 |
"target_language_name":"Igbo",
|
484 |
"bleu":46.4017344934,
|
|
|
485 |
"speakers":27000000.0
|
486 |
},
|
487 |
{
|
488 |
"target_language_name":"Ilocano",
|
489 |
"bleu":62.6058864594,
|
|
|
490 |
"speakers":9100000.0
|
491 |
},
|
492 |
{
|
493 |
"target_language_name":"Indonesian",
|
494 |
"bleu":72.9087066262,
|
|
|
495 |
"speakers":198996550.0
|
496 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
497 |
{
|
498 |
"target_language_name":"Irish",
|
499 |
"bleu":69.9725194524,
|
|
|
500 |
"speakers":1030000.0
|
501 |
},
|
502 |
{
|
503 |
"target_language_name":"Italian",
|
504 |
"bleu":69.1588343572,
|
|
|
505 |
"speakers":64819790.0
|
506 |
},
|
507 |
{
|
508 |
"target_language_name":"Japanese",
|
509 |
"bleu":49.9166135693,
|
|
|
510 |
"speakers":128000000.0
|
511 |
},
|
512 |
{
|
513 |
"target_language_name":"Javanese",
|
514 |
"bleu":60.440335299,
|
|
|
515 |
"speakers":84308740.0
|
516 |
},
|
517 |
{
|
518 |
"target_language_name":"Jingpho",
|
519 |
"bleu":43.5500581403,
|
|
|
520 |
"speakers":940000.0
|
521 |
},
|
522 |
{
|
523 |
"target_language_name":"Jula",
|
524 |
"bleu":29.5415180297,
|
|
|
525 |
"speakers":2700000.0
|
526 |
},
|
527 |
{
|
528 |
"target_language_name":"Kabiy\u00e8",
|
529 |
"bleu":22.5498504655,
|
|
|
530 |
"speakers":1000000.0
|
531 |
},
|
532 |
{
|
533 |
"target_language_name":"Kabuverdianu",
|
534 |
"bleu":65.1106010391,
|
|
|
535 |
"speakers":871000.0
|
536 |
},
|
537 |
{
|
538 |
"target_language_name":"Kabyle",
|
539 |
"bleu":41.1442992587,
|
|
|
540 |
"speakers":5586000.0
|
541 |
},
|
542 |
{
|
543 |
"target_language_name":"Kamba",
|
544 |
"bleu":41.733489671,
|
|
|
545 |
"speakers":3893000.0
|
546 |
},
|
547 |
{
|
548 |
"target_language_name":"Kannada",
|
549 |
"bleu":60.0142028332,
|
|
|
550 |
"speakers":43600000.0
|
551 |
},
|
552 |
{
|
553 |
"target_language_name":"Kashmiri",
|
554 |
"bleu":22.3019416547,
|
|
|
555 |
"speakers":6900000.0
|
556 |
},
|
557 |
{
|
558 |
"target_language_name":"Kazakh",
|
559 |
"bleu":61.1251621375,
|
|
|
560 |
"speakers":13161980.0
|
561 |
},
|
562 |
{
|
563 |
"target_language_name":"Khmer",
|
564 |
"bleu":49.2098257043,
|
|
|
565 |
"speakers":16600000.0
|
566 |
},
|
567 |
{
|
568 |
"target_language_name":"Kimbundu",
|
569 |
"bleu":5.8523457224,
|
|
|
570 |
"speakers":0.0
|
571 |
},
|
572 |
{
|
573 |
"target_language_name":"Kinyarwanda",
|
574 |
"bleu":57.2410626756,
|
|
|
575 |
"speakers":12100000.0
|
576 |
},
|
577 |
{
|
578 |
"target_language_name":"Kituba (Democratic Republic of the Congo)",
|
579 |
"bleu":52.8484601602,
|
|
|
580 |
"speakers":0.0
|
581 |
},
|
582 |
{
|
583 |
"target_language_name":"Korean",
|
584 |
"bleu":43.6872285974,
|
|
|
585 |
"speakers":77300000.0
|
586 |
},
|
587 |
{
|
588 |
"target_language_name":"Kyrgyz",
|
589 |
"bleu":57.0824422453,
|
|
|
590 |
"speakers":4568480.0
|
591 |
},
|
592 |
{
|
593 |
"target_language_name":"Lao",
|
594 |
"bleu":60.0210909677,
|
|
|
595 |
"speakers":5225552.0
|
596 |
},
|
597 |
{
|
598 |
"target_language_name":"Latgalian",
|
599 |
"bleu":56.4843556524,
|
|
|
600 |
"speakers":200000.0
|
601 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
602 |
{
|
603 |
"target_language_name":"Ligurian",
|
604 |
"bleu":55.8530636302,
|
|
|
605 |
"speakers":500000.0
|
606 |
},
|
607 |
{
|
608 |
"target_language_name":"Limburgish",
|
609 |
"bleu":59.4485504982,
|
|
|
610 |
"speakers":1600000.0
|
611 |
},
|
612 |
{
|
613 |
"target_language_name":"Lingala",
|
614 |
"bleu":30.4322896531,
|
|
|
615 |
"speakers":20000000.0
|
616 |
},
|
617 |
{
|
618 |
"target_language_name":"Lithuanian",
|
619 |
"bleu":67.1625695571,
|
|
|
620 |
"speakers":4000000.0
|
621 |
},
|
622 |
{
|
623 |
"target_language_name":"Lombard",
|
624 |
"bleu":46.3884402674,
|
|
|
625 |
"speakers":3900000.0
|
626 |
},
|
627 |
{
|
628 |
"target_language_name":"Luba-Kasai",
|
629 |
"bleu":45.0655291655,
|
|
|
630 |
"speakers":6300000.0
|
631 |
},
|
632 |
{
|
633 |
"target_language_name":"Luxembourgish",
|
634 |
"bleu":70.8338190438,
|
|
|
635 |
"speakers":391200.0
|
636 |
},
|
637 |
{
|
638 |
"target_language_name":"Macedonian",
|
639 |
"bleu":72.2733471437,
|
|
|
640 |
"speakers":2000000.0
|
641 |
},
|
642 |
{
|
643 |
"target_language_name":"Magahi",
|
644 |
"bleu":58.5474221546,
|
|
|
645 |
"speakers":20700000.0
|
646 |
},
|
647 |
{
|
648 |
"target_language_name":"Maithili",
|
649 |
"bleu":54.6530071391,
|
|
|
650 |
"speakers":33900000.0
|
651 |
},
|
652 |
{
|
653 |
"target_language_name":"Malayalam",
|
654 |
"bleu":64.0655894091,
|
|
|
655 |
"speakers":37100000.0
|
656 |
},
|
657 |
{
|
658 |
"target_language_name":"Maltese",
|
659 |
"bleu":80.0866777263,
|
|
|
660 |
"speakers":570000.0
|
661 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
662 |
{
|
663 |
"target_language_name":"Maori",
|
664 |
"bleu":54.8319935643,
|
|
|
665 |
"speakers":160000.0
|
666 |
},
|
667 |
{
|
668 |
"target_language_name":"Marathi",
|
669 |
"bleu":57.4434090711,
|
|
|
670 |
"speakers":83100000.0
|
671 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
672 |
{
|
673 |
"target_language_name":"Meitei",
|
674 |
"bleu":41.2619945571,
|
|
|
675 |
"speakers":1470000.0
|
676 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
677 |
{
|
678 |
"target_language_name":"Minangkabau",
|
679 |
"bleu":50.7407956197,
|
|
|
680 |
"speakers":5530000.0
|
681 |
},
|
682 |
{
|
683 |
"target_language_name":"Mizo",
|
684 |
"bleu":51.6558017488,
|
|
|
685 |
"speakers":500000.0
|
686 |
},
|
687 |
{
|
688 |
"target_language_name":"Moore",
|
689 |
"bleu":32.8458097983,
|
|
|
690 |
"speakers":7600000.0
|
691 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
692 |
{
|
693 |
"target_language_name":"Nepali",
|
694 |
"bleu":55.2919347352,
|
|
|
695 |
"speakers":0.0
|
696 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
697 |
{
|
698 |
"target_language_name":"Nuer",
|
699 |
"bleu":16.5796987951,
|
|
|
700 |
"speakers":900000.0
|
701 |
},
|
702 |
{
|
703 |
"target_language_name":"N\u2019Ko",
|
704 |
"bleu":32.483490799,
|
|
|
705 |
"speakers":0.0
|
706 |
},
|
707 |
{
|
708 |
"target_language_name":"Occitan",
|
709 |
"bleu":71.532740184,
|
|
|
710 |
"speakers":542000.0
|
711 |
},
|
712 |
{
|
713 |
"target_language_name":"Odia",
|
714 |
"bleu":57.3628096518,
|
|
|
715 |
"speakers":34500000.0
|
716 |
},
|
717 |
{
|
718 |
"target_language_name":"Pangasinan",
|
719 |
"bleu":56.0048183827,
|
|
|
720 |
"speakers":1100000.0
|
721 |
},
|
722 |
{
|
723 |
"target_language_name":"Papiamentu",
|
724 |
"bleu":69.7955328133,
|
|
|
725 |
"speakers":321300.0
|
726 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
727 |
{
|
728 |
"target_language_name":"Polish",
|
729 |
"bleu":61.8768399674,
|
|
|
730 |
"speakers":40200000.0
|
731 |
},
|
732 |
{
|
733 |
"target_language_name":"Portuguese",
|
734 |
"bleu":77.4978074222,
|
|
|
735 |
"speakers":254300000.0
|
736 |
},
|
737 |
{
|
738 |
"target_language_name":"Romanian",
|
739 |
"bleu":76.4907159035,
|
|
|
740 |
"speakers":24300000.0
|
741 |
},
|
742 |
{
|
743 |
"target_language_name":"Rundi",
|
744 |
"bleu":48.943513629,
|
|
|
745 |
"speakers":10800000.0
|
746 |
},
|
747 |
{
|
748 |
"target_language_name":"Russian",
|
749 |
"bleu":71.1489441039,
|
|
|
750 |
"speakers":171428900.0
|
751 |
},
|
752 |
{
|
753 |
"target_language_name":"Samoan",
|
754 |
"bleu":56.7138831423,
|
|
|
755 |
"speakers":415720.0
|
756 |
},
|
757 |
{
|
758 |
"target_language_name":"Sango",
|
759 |
"bleu":34.8754222657,
|
|
|
760 |
"speakers":4600000.0
|
761 |
},
|
762 |
{
|
763 |
"target_language_name":"Sanskrit",
|
764 |
"bleu":32.7813249911,
|
|
|
765 |
"speakers":49736.0
|
766 |
},
|
767 |
{
|
768 |
"target_language_name":"Santhali",
|
769 |
"bleu":31.5119247269,
|
|
|
770 |
"speakers":7200000.0
|
771 |
},
|
772 |
{
|
773 |
"target_language_name":"Sardinian",
|
774 |
"bleu":62.6903914771,
|
|
|
775 |
"speakers":1300000.0
|
776 |
},
|
777 |
{
|
778 |
"target_language_name":"Scottish Gaelic",
|
779 |
"bleu":62.6044371338,
|
|
|
780 |
"speakers":60130.0
|
781 |
},
|
782 |
{
|
783 |
"target_language_name":"Serbian",
|
784 |
"bleu":69.9691396176,
|
|
|
785 |
"speakers":9000000.0
|
786 |
},
|
787 |
{
|
788 |
"target_language_name":"Setswana",
|
789 |
"bleu":55.2288890228,
|
|
|
790 |
"speakers":4500000.0
|
791 |
},
|
792 |
{
|
793 |
"target_language_name":"Shan",
|
794 |
"bleu":29.2129948577,
|
|
|
795 |
"speakers":3000000.0
|
796 |
},
|
797 |
{
|
798 |
"target_language_name":"Shona",
|
799 |
"bleu":51.5592191405,
|
|
|
800 |
"speakers":9023000.0
|
801 |
},
|
802 |
{
|
803 |
"target_language_name":"Sicilian",
|
804 |
"bleu":58.5895359443,
|
|
|
805 |
"speakers":4700000.0
|
806 |
},
|
807 |
{
|
808 |
"target_language_name":"Silesian",
|
809 |
"bleu":56.7836392069,
|
|
|
810 |
"speakers":522000.0
|
811 |
},
|
812 |
{
|
813 |
"target_language_name":"Sindhi",
|
814 |
"bleu":48.1876056648,
|
|
|
815 |
"speakers":25000000.0
|
816 |
},
|
817 |
{
|
818 |
"target_language_name":"Sinhala",
|
819 |
"bleu":56.7567311796,
|
|
|
820 |
"speakers":15300000.0
|
821 |
},
|
822 |
{
|
823 |
"target_language_name":"Slovak",
|
824 |
"bleu":67.9284804086,
|
|
|
825 |
"speakers":6000000.0
|
826 |
},
|
827 |
{
|
828 |
"target_language_name":"Slovene",
|
829 |
"bleu":72.5691270757,
|
|
|
830 |
"speakers":2400000.0
|
831 |
},
|
832 |
{
|
833 |
"target_language_name":"Somali",
|
834 |
"bleu":55.3706496473,
|
|
|
835 |
"speakers":16200000.0
|
836 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
837 |
{
|
838 |
"target_language_name":"Spanish",
|
839 |
"bleu":63.8467073379,
|
|
|
840 |
"speakers":485000000.0
|
841 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
842 |
{
|
843 |
"target_language_name":"Sunda",
|
844 |
"bleu":56.4065999104,
|
|
|
845 |
"speakers":32400000.0
|
846 |
},
|
847 |
{
|
848 |
"target_language_name":"Swahili",
|
849 |
"bleu":73.5199042142,
|
|
|
850 |
"speakers":82300000.0
|
851 |
},
|
852 |
{
|
853 |
"target_language_name":"Swati",
|
854 |
"bleu":52.7746096439,
|
|
|
855 |
"speakers":2034200.0
|
856 |
},
|
857 |
{
|
858 |
"target_language_name":"Swedish",
|
859 |
"bleu":77.421610247,
|
|
|
860 |
"speakers":9244250.0
|
861 |
},
|
862 |
{
|
863 |
"target_language_name":"Tajik",
|
864 |
"bleu":60.9783684158,
|
|
|
865 |
"speakers":14000000.0
|
866 |
},
|
867 |
{
|
868 |
"target_language_name":"Tamasheq",
|
869 |
"bleu":18.4319889721,
|
|
|
870 |
"speakers":500000.0
|
871 |
},
|
872 |
{
|
873 |
"target_language_name":"Tamil",
|
874 |
"bleu":65.7863221054,
|
|
|
875 |
"speakers":75000000.0
|
876 |
},
|
877 |
{
|
878 |
"target_language_name":"Tatar",
|
879 |
"bleu":60.3447467213,
|
|
|
880 |
"speakers":5427318.0
|
881 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
882 |
{
|
883 |
"target_language_name":"Telugu",
|
884 |
"bleu":61.6352457629,
|
|
|
885 |
"speakers":82000000.0
|
886 |
},
|
887 |
{
|
888 |
"target_language_name":"Thai",
|
889 |
"bleu":62.8125360944,
|
|
|
890 |
"speakers":40000000.0
|
891 |
},
|
892 |
{
|
893 |
"target_language_name":"Tigrigna",
|
894 |
"bleu":32.8711961703,
|
|
|
895 |
"speakers":7507780.0
|
896 |
},
|
897 |
{
|
898 |
"target_language_name":"Tok Pisin",
|
899 |
"bleu":56.5407760367,
|
|
|
900 |
"speakers":4000000.0
|
901 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
902 |
{
|
903 |
"target_language_name":"Tsonga",
|
904 |
"bleu":58.3516573597,
|
|
|
905 |
"speakers":13000000.0
|
906 |
},
|
907 |
{
|
908 |
"target_language_name":"Tumbuka",
|
909 |
"bleu":44.0490017392,
|
|
|
910 |
"speakers":2680000.0
|
911 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
912 |
{
|
913 |
"target_language_name":"Turkish",
|
914 |
"bleu":67.1600625676,
|
|
|
915 |
"speakers":82231620.0
|
916 |
},
|
917 |
{
|
918 |
"target_language_name":"Turkmen",
|
919 |
"bleu":60.5593705936,
|
|
|
920 |
"speakers":16000000.0
|
921 |
},
|
922 |
{
|
923 |
"target_language_name":"Twi",
|
924 |
"bleu":44.7976562068,
|
|
|
925 |
"speakers":3000000.0
|
926 |
},
|
927 |
{
|
928 |
"target_language_name":"Ukrainian",
|
929 |
"bleu":68.0976232544,
|
|
|
930 |
"speakers":34710100.0
|
931 |
},
|
932 |
{
|
933 |
"target_language_name":"Umbundu",
|
934 |
"bleu":21.0802775597,
|
|
|
935 |
"speakers":6000000.0
|
936 |
},
|
937 |
{
|
938 |
"target_language_name":"Urdu",
|
939 |
"bleu":61.1255457272,
|
|
|
940 |
"speakers":94022900.0
|
941 |
},
|
942 |
{
|
943 |
"target_language_name":"Uyghur",
|
944 |
"bleu":53.5346877103,
|
|
|
945 |
"speakers":10400000.0
|
946 |
},
|
947 |
{
|
948 |
"target_language_name":"Venetian",
|
949 |
"bleu":60.6140876271,
|
|
|
950 |
"speakers":2000000.0
|
951 |
},
|
952 |
{
|
953 |
"target_language_name":"Vietnamese",
|
954 |
"bleu":70.3560749464,
|
|
|
955 |
"speakers":76000000.0
|
956 |
},
|
957 |
{
|
958 |
"target_language_name":"Waray-Waray",
|
959 |
"bleu":66.3850231243,
|
|
|
960 |
"speakers":3100000.0
|
961 |
},
|
962 |
{
|
963 |
"target_language_name":"Welsh",
|
964 |
"bleu":83.3437724474,
|
|
|
965 |
"speakers":977366.0
|
966 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
967 |
{
|
968 |
"target_language_name":"Wolof",
|
969 |
"bleu":42.6430127569,
|
|
|
970 |
"speakers":3700000.0
|
971 |
},
|
972 |
{
|
973 |
"target_language_name":"Xhosa",
|
974 |
"bleu":55.4688091009,
|
|
|
975 |
"speakers":11000000.0
|
976 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
977 |
{
|
978 |
"target_language_name":"Yoruba",
|
979 |
"bleu":34.2642542268,
|
|
|
980 |
"speakers":40000000.0
|
981 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
982 |
{
|
983 |
"target_language_name":"Zulu",
|
984 |
"bleu":59.1762078389,
|
|
|
985 |
"speakers":15700000.0
|
986 |
},
|
987 |
{
|
988 |
"target_language_name":"nno",
|
989 |
"bleu":71.8615646296,
|
|
|
990 |
"speakers":0.0
|
991 |
},
|
992 |
{
|
993 |
"target_language_name":"\u00c9w\u00e9",
|
994 |
"bleu":41.6614038791,
|
|
|
995 |
"speakers":3000000.0
|
996 |
}
|
997 |
]
|
|
|
1 |
[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
{
|
3 |
"target_language_name":"Aceh",
|
4 |
"bleu":39.1659660901,
|
5 |
+
"bert_score":0.8998966595,
|
6 |
"speakers":3500032.0
|
7 |
},
|
8 |
{
|
9 |
"target_language_name":"Afrikaans",
|
10 |
"bleu":76.8900540777,
|
11 |
+
"bert_score":0.9481831173,
|
12 |
"speakers":10300000.0
|
13 |
},
|
14 |
{
|
15 |
"target_language_name":"Amharic",
|
16 |
"bleu":43.1544568697,
|
17 |
+
"bert_score":0.989116921,
|
18 |
"speakers":25000000.0
|
19 |
},
|
20 |
{
|
21 |
"target_language_name":"Armenian",
|
22 |
"bleu":64.6804400806,
|
23 |
+
"bert_score":0.9550812801,
|
24 |
"speakers":6700000.0
|
25 |
},
|
26 |
{
|
27 |
"target_language_name":"Assamese",
|
28 |
"bleu":47.0351331605,
|
29 |
+
"bert_score":0.928119574,
|
30 |
"speakers":15300000.0
|
31 |
},
|
32 |
{
|
33 |
"target_language_name":"Asturian",
|
34 |
"bleu":71.3445623493,
|
35 |
+
"bert_score":0.931475842,
|
36 |
"speakers":450000.0
|
37 |
},
|
38 |
{
|
39 |
"target_language_name":"Awadhi",
|
40 |
"bleu":46.0797144146,
|
41 |
+
"bert_score":0.9333642821,
|
42 |
"speakers":22000000.0
|
43 |
},
|
44 |
+
{
|
45 |
+
"target_language_name":"Ayacucho Quechua",
|
46 |
+
"bleu":45.6534927028,
|
47 |
+
"bert_score":0.8731370111,
|
48 |
+
"speakers":918200.0
|
49 |
+
},
|
50 |
{
|
51 |
"target_language_name":"Bali (Indonesia)",
|
52 |
"bleu":52.8752419159,
|
53 |
+
"bert_score":0.8934772114,
|
54 |
"speakers":4000000.0
|
55 |
},
|
56 |
{
|
57 |
"target_language_name":"Bamanankan",
|
58 |
"bleu":38.6939091408,
|
59 |
+
"bert_score":0.8872043769,
|
60 |
"speakers":2700000.0
|
61 |
},
|
62 |
{
|
63 |
"target_language_name":"Banjar",
|
64 |
"bleu":46.5453977487,
|
65 |
+
"bert_score":0.91599799,
|
66 |
"speakers":3500000.0
|
67 |
},
|
68 |
{
|
69 |
"target_language_name":"Bashkort",
|
70 |
"bleu":57.5453842927,
|
71 |
+
"bert_score":0.9298217595,
|
72 |
"speakers":1200000.0
|
73 |
},
|
74 |
{
|
75 |
"target_language_name":"Basque",
|
76 |
"bleu":65.8968721377,
|
77 |
+
"bert_score":0.9192741295,
|
78 |
"speakers":750000.0
|
79 |
},
|
80 |
{
|
81 |
"target_language_name":"Belarusian",
|
82 |
"bleu":54.5195166442,
|
83 |
+
"bert_score":0.9329862595,
|
84 |
"speakers":7900000.0
|
85 |
},
|
86 |
{
|
87 |
"target_language_name":"Bemba",
|
88 |
"bleu":47.8068548956,
|
89 |
+
"bert_score":0.889907831,
|
90 |
"speakers":3600000.0
|
91 |
},
|
92 |
{
|
93 |
"target_language_name":"Bengali",
|
94 |
"bleu":57.1417588816,
|
95 |
+
"bert_score":0.9483523647,
|
96 |
"speakers":300000000.0
|
97 |
},
|
98 |
{
|
99 |
"target_language_name":"Bhojpuri",
|
100 |
"bleu":44.5412337907,
|
101 |
+
"bert_score":0.9288184981,
|
102 |
"speakers":52200000.0
|
103 |
},
|
104 |
{
|
105 |
"target_language_name":"Bokm\u00e5l",
|
106 |
"bleu":77.4939513016,
|
107 |
+
"bert_score":0.9550971886,
|
108 |
"speakers":4000000.0
|
109 |
},
|
110 |
{
|
111 |
"target_language_name":"Boro (India)",
|
112 |
"bleu":36.1100474969,
|
113 |
+
"bert_score":0.925187854,
|
114 |
"speakers":1482929.0
|
115 |
},
|
116 |
{
|
117 |
"target_language_name":"Bosnian",
|
118 |
"bleu":72.5488027131,
|
119 |
+
"bert_score":0.947693936,
|
120 |
"speakers":3500000.0
|
121 |
},
|
122 |
{
|
123 |
"target_language_name":"Bugis",
|
124 |
"bleu":44.8388170031,
|
125 |
+
"bert_score":0.8647923966,
|
126 |
"speakers":5017800.0
|
127 |
},
|
128 |
{
|
129 |
"target_language_name":"Bulgarian",
|
130 |
"bleu":72.9695925131,
|
131 |
+
"bert_score":0.9545443177,
|
132 |
"speakers":9000000.0
|
133 |
},
|
134 |
{
|
135 |
"target_language_name":"Burmese",
|
136 |
"bleu":55.7235911677,
|
137 |
+
"bert_score":0.9759751062,
|
138 |
"speakers":32900000.0
|
139 |
},
|
140 |
{
|
141 |
"target_language_name":"Catalan",
|
142 |
"bleu":74.4595007932,
|
143 |
+
"bert_score":0.9464139263,
|
144 |
"speakers":5100000.0
|
145 |
},
|
146 |
{
|
147 |
"target_language_name":"Cebuano",
|
148 |
"bleu":69.4557958655,
|
149 |
+
"bert_score":0.9321281234,
|
150 |
"speakers":15900000.0
|
151 |
},
|
152 |
+
{
|
153 |
+
"target_language_name":"Central Aymara",
|
154 |
+
"bleu":42.7698436669,
|
155 |
+
"bert_score":0.8625142018,
|
156 |
+
"speakers":0.0
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"target_language_name":"Central Kurdish",
|
160 |
+
"bleu":59.1927910692,
|
161 |
+
"bert_score":0.9332568824,
|
162 |
+
"speakers":7250000.0
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"target_language_name":"Central Tibetan",
|
166 |
+
"bleu":51.349075274,
|
167 |
+
"bert_score":0.967157503,
|
168 |
+
"speakers":1200000.0
|
169 |
+
},
|
170 |
{
|
171 |
"target_language_name":"Chhattisgarhi",
|
172 |
"bleu":47.9797501304,
|
173 |
+
"bert_score":0.9363766015,
|
174 |
"speakers":16300000.0
|
175 |
},
|
176 |
{
|
177 |
"target_language_name":"Chichewa",
|
178 |
"bleu":59.7601680161,
|
179 |
+
"bert_score":0.9069253902,
|
180 |
"speakers":12000000.0
|
181 |
},
|
182 |
{
|
183 |
"target_language_name":"Chokwe",
|
184 |
"bleu":10.1864074161,
|
185 |
+
"bert_score":0.727788798,
|
186 |
"speakers":0.0
|
187 |
},
|
188 |
{
|
189 |
"target_language_name":"Chuvash",
|
190 |
"bleu":45.0546658723,
|
191 |
+
"bert_score":0.9203916192,
|
192 |
"speakers":1279650.0
|
193 |
},
|
194 |
{
|
195 |
"target_language_name":"Crimean Tatar",
|
196 |
"bleu":52.7050249448,
|
197 |
+
"bert_score":0.8972040812,
|
198 |
"speakers":552740.0
|
199 |
},
|
200 |
{
|
201 |
"target_language_name":"Croatian",
|
202 |
"bleu":69.5456983662,
|
203 |
+
"bert_score":0.9444877982,
|
204 |
"speakers":7000000.0
|
205 |
},
|
206 |
{
|
207 |
"target_language_name":"Czech",
|
208 |
"bleu":69.7112290599,
|
209 |
+
"bert_score":0.9384464244,
|
210 |
"speakers":10700000.0
|
211 |
},
|
212 |
{
|
213 |
"target_language_name":"Danish",
|
214 |
"bleu":78.0935433284,
|
215 |
+
"bert_score":0.9506490747,
|
216 |
"speakers":6000000.0
|
217 |
},
|
218 |
{
|
219 |
"target_language_name":"Dari",
|
220 |
"bleu":52.5539795795,
|
221 |
+
"bert_score":0.9466466506,
|
222 |
"speakers":9600000.0
|
223 |
},
|
224 |
{
|
225 |
"target_language_name":"Dholuo",
|
226 |
"bleu":46.4119479071,
|
227 |
+
"bert_score":0.8803233822,
|
228 |
"speakers":3000000.0
|
229 |
},
|
230 |
{
|
231 |
"target_language_name":"Dogri",
|
232 |
"bleu":44.9153535278,
|
233 |
+
"bert_score":0.934070154,
|
234 |
"speakers":2000000.0
|
235 |
},
|
236 |
{
|
237 |
"target_language_name":"Dutch",
|
238 |
"bleu":71.1849326315,
|
239 |
+
"bert_score":0.9376831949,
|
240 |
"speakers":23100000.0
|
241 |
},
|
242 |
{
|
243 |
"target_language_name":"Dzongkha",
|
244 |
"bleu":44.3573814017,
|
245 |
+
"bert_score":0.9664796074,
|
246 |
"speakers":237080.0
|
247 |
},
|
248 |
+
{
|
249 |
+
"target_language_name":"Eastern Punjabi",
|
250 |
+
"bleu":60.468441109,
|
251 |
+
"bert_score":0.988244007,
|
252 |
+
"speakers":125000000.0
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"target_language_name":"Eastern Yiddish",
|
256 |
+
"bleu":47.5562009325,
|
257 |
+
"bert_score":0.9590989411,
|
258 |
+
"speakers":0.0
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"target_language_name":"Egyptian Arabic",
|
262 |
+
"bleu":53.6818081038,
|
263 |
+
"bert_score":0.9394114673,
|
264 |
+
"speakers":100542400.0
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"target_language_name":"English",
|
268 |
+
"bleu":75.3501173486,
|
269 |
+
"bert_score":0.8807334363,
|
270 |
+
"speakers":1132366680.0
|
271 |
+
},
|
272 |
{
|
273 |
"target_language_name":"Esperanto",
|
274 |
"bleu":69.6056577554,
|
275 |
+
"bert_score":0.9302131255,
|
276 |
"speakers":2000000.0
|
277 |
},
|
278 |
{
|
279 |
"target_language_name":"Faroese",
|
280 |
"bleu":65.9147902483,
|
281 |
+
"bert_score":0.9332413753,
|
282 |
"speakers":69150.0
|
283 |
},
|
284 |
{
|
285 |
"target_language_name":"Fijian",
|
286 |
"bleu":58.2892667246,
|
287 |
+
"bert_score":0.9183188617,
|
288 |
"speakers":341270.0
|
289 |
},
|
290 |
{
|
291 |
"target_language_name":"Filipino",
|
292 |
"bleu":70.1928498378,
|
293 |
+
"bert_score":0.9269425154,
|
294 |
"speakers":90000000.0
|
295 |
},
|
296 |
{
|
297 |
"target_language_name":"Finnish",
|
298 |
"bleu":70.9425029518,
|
299 |
+
"bert_score":0.9320579688,
|
300 |
"speakers":5413380.0
|
301 |
},
|
302 |
{
|
303 |
"target_language_name":"Fon",
|
304 |
"bleu":25.2797773666,
|
305 |
+
"bert_score":0.8664443592,
|
306 |
"speakers":1935500.0
|
307 |
},
|
308 |
{
|
309 |
"target_language_name":"French",
|
310 |
"bleu":79.3023871219,
|
311 |
+
"bert_score":0.9554367423,
|
312 |
"speakers":208157220.0
|
313 |
},
|
314 |
{
|
315 |
"target_language_name":"Friulian",
|
316 |
"bleu":66.5488092372,
|
317 |
+
"bert_score":0.9255799611,
|
318 |
"speakers":300000.0
|
319 |
},
|
320 |
{
|
321 |
"target_language_name":"Galician",
|
322 |
"bleu":68.7024786904,
|
323 |
+
"bert_score":0.9283550183,
|
324 |
"speakers":2500000.0
|
325 |
},
|
326 |
{
|
327 |
"target_language_name":"Ganda",
|
328 |
"bleu":45.8693322936,
|
329 |
+
"bert_score":0.88344028,
|
330 |
"speakers":4100000.0
|
331 |
},
|
332 |
{
|
333 |
"target_language_name":"Georgian",
|
334 |
"bleu":61.0166361442,
|
335 |
+
"bert_score":0.9546662311,
|
336 |
"speakers":3700000.0
|
337 |
},
|
338 |
{
|
339 |
"target_language_name":"Gikuyu",
|
340 |
"bleu":40.9288275291,
|
341 |
+
"bert_score":0.8850945433,
|
342 |
"speakers":6623000.0
|
343 |
},
|
344 |
+
{
|
345 |
+
"target_language_name":"Goan Konkani",
|
346 |
+
"bleu":47.1084017945,
|
347 |
+
"bert_score":0.9314287245,
|
348 |
+
"speakers":3633900.0
|
349 |
+
},
|
350 |
{
|
351 |
"target_language_name":"Greek",
|
352 |
"bleu":66.2347782153,
|
353 |
+
"bert_score":0.9577525119,
|
354 |
"speakers":15000000.0
|
355 |
},
|
356 |
{
|
357 |
"target_language_name":"Gujarati",
|
358 |
"bleu":55.5884513452,
|
359 |
+
"bert_score":0.9753397226,
|
360 |
"speakers":56400000.0
|
361 |
},
|
362 |
{
|
363 |
"target_language_name":"Haitian Creole",
|
364 |
"bleu":63.8532187591,
|
365 |
+
"bert_score":0.93236112,
|
366 |
"speakers":9600000.0
|
367 |
},
|
368 |
+
{
|
369 |
+
"target_language_name":"Halh Mongolian",
|
370 |
+
"bleu":58.5037789971,
|
371 |
+
"bert_score":0.9380823056,
|
372 |
+
"speakers":2704030.0
|
373 |
+
},
|
374 |
{
|
375 |
"target_language_name":"Hausa",
|
376 |
"bleu":56.3431957901,
|
377 |
+
"bert_score":0.9012877802,
|
378 |
"speakers":43900000.0
|
379 |
},
|
380 |
{
|
381 |
"target_language_name":"Hebrew",
|
382 |
"bleu":72.0702990513,
|
383 |
+
"bert_score":0.964064618,
|
384 |
"speakers":9303950.0
|
385 |
},
|
386 |
{
|
387 |
"target_language_name":"Hindi",
|
388 |
"bleu":64.9362166898,
|
389 |
+
"bert_score":0.9463364283,
|
390 |
"speakers":341000000.0
|
391 |
},
|
392 |
{
|
393 |
"target_language_name":"Hungarian",
|
394 |
"bleu":66.1301119408,
|
395 |
+
"bert_score":0.9249218643,
|
396 |
"speakers":12600000.0
|
397 |
},
|
398 |
{
|
399 |
"target_language_name":"Icelandic",
|
400 |
"bleu":54.4330055353,
|
401 |
+
"bert_score":0.9120460276,
|
402 |
"speakers":358000.0
|
403 |
},
|
404 |
{
|
405 |
"target_language_name":"Igbo",
|
406 |
"bleu":46.4017344934,
|
407 |
+
"bert_score":0.9137314638,
|
408 |
"speakers":27000000.0
|
409 |
},
|
410 |
{
|
411 |
"target_language_name":"Ilocano",
|
412 |
"bleu":62.6058864594,
|
413 |
+
"bert_score":0.9115280092,
|
414 |
"speakers":9100000.0
|
415 |
},
|
416 |
{
|
417 |
"target_language_name":"Indonesian",
|
418 |
"bleu":72.9087066262,
|
419 |
+
"bert_score":0.9301403503,
|
420 |
"speakers":198996550.0
|
421 |
},
|
422 |
+
{
|
423 |
+
"target_language_name":"Iranian Persian",
|
424 |
+
"bleu":57.6444169698,
|
425 |
+
"bert_score":0.9476486345,
|
426 |
+
"speakers":52800000.0
|
427 |
+
},
|
428 |
{
|
429 |
"target_language_name":"Irish",
|
430 |
"bleu":69.9725194524,
|
431 |
+
"bert_score":0.9440232972,
|
432 |
"speakers":1030000.0
|
433 |
},
|
434 |
{
|
435 |
"target_language_name":"Italian",
|
436 |
"bleu":69.1588343572,
|
437 |
+
"bert_score":0.9358606537,
|
438 |
"speakers":64819790.0
|
439 |
},
|
440 |
{
|
441 |
"target_language_name":"Japanese",
|
442 |
"bleu":49.9166135693,
|
443 |
+
"bert_score":0.9425287286,
|
444 |
"speakers":128000000.0
|
445 |
},
|
446 |
{
|
447 |
"target_language_name":"Javanese",
|
448 |
"bleu":60.440335299,
|
449 |
+
"bert_score":0.9125308077,
|
450 |
"speakers":84308740.0
|
451 |
},
|
452 |
{
|
453 |
"target_language_name":"Jingpho",
|
454 |
"bleu":43.5500581403,
|
455 |
+
"bert_score":0.8727998992,
|
456 |
"speakers":940000.0
|
457 |
},
|
458 |
{
|
459 |
"target_language_name":"Jula",
|
460 |
"bleu":29.5415180297,
|
461 |
+
"bert_score":0.822332112,
|
462 |
"speakers":2700000.0
|
463 |
},
|
464 |
{
|
465 |
"target_language_name":"Kabiy\u00e8",
|
466 |
"bleu":22.5498504655,
|
467 |
+
"bert_score":0.8587520639,
|
468 |
"speakers":1000000.0
|
469 |
},
|
470 |
{
|
471 |
"target_language_name":"Kabuverdianu",
|
472 |
"bleu":65.1106010391,
|
473 |
+
"bert_score":0.9213403026,
|
474 |
"speakers":871000.0
|
475 |
},
|
476 |
{
|
477 |
"target_language_name":"Kabyle",
|
478 |
"bleu":41.1442992587,
|
479 |
+
"bert_score":0.8803219795,
|
480 |
"speakers":5586000.0
|
481 |
},
|
482 |
{
|
483 |
"target_language_name":"Kamba",
|
484 |
"bleu":41.733489671,
|
485 |
+
"bert_score":0.8780206362,
|
486 |
"speakers":3893000.0
|
487 |
},
|
488 |
{
|
489 |
"target_language_name":"Kannada",
|
490 |
"bleu":60.0142028332,
|
491 |
+
"bert_score":0.9730932295,
|
492 |
"speakers":43600000.0
|
493 |
},
|
494 |
{
|
495 |
"target_language_name":"Kashmiri",
|
496 |
"bleu":22.3019416547,
|
497 |
+
"bert_score":0.8984790143,
|
498 |
"speakers":6900000.0
|
499 |
},
|
500 |
{
|
501 |
"target_language_name":"Kazakh",
|
502 |
"bleu":61.1251621375,
|
503 |
+
"bert_score":0.9379647116,
|
504 |
"speakers":13161980.0
|
505 |
},
|
506 |
{
|
507 |
"target_language_name":"Khmer",
|
508 |
"bleu":49.2098257043,
|
509 |
+
"bert_score":0.8907732884,
|
510 |
"speakers":16600000.0
|
511 |
},
|
512 |
{
|
513 |
"target_language_name":"Kimbundu",
|
514 |
"bleu":5.8523457224,
|
515 |
+
"bert_score":0.6849321783,
|
516 |
"speakers":0.0
|
517 |
},
|
518 |
{
|
519 |
"target_language_name":"Kinyarwanda",
|
520 |
"bleu":57.2410626756,
|
521 |
+
"bert_score":0.906923449,
|
522 |
"speakers":12100000.0
|
523 |
},
|
524 |
{
|
525 |
"target_language_name":"Kituba (Democratic Republic of the Congo)",
|
526 |
"bleu":52.8484601602,
|
527 |
+
"bert_score":0.9017938395,
|
528 |
"speakers":0.0
|
529 |
},
|
530 |
{
|
531 |
"target_language_name":"Korean",
|
532 |
"bleu":43.6872285974,
|
533 |
+
"bert_score":0.9579092761,
|
534 |
"speakers":77300000.0
|
535 |
},
|
536 |
{
|
537 |
"target_language_name":"Kyrgyz",
|
538 |
"bleu":57.0824422453,
|
539 |
+
"bert_score":0.9317750076,
|
540 |
"speakers":4568480.0
|
541 |
},
|
542 |
{
|
543 |
"target_language_name":"Lao",
|
544 |
"bleu":60.0210909677,
|
545 |
+
"bert_score":0.904438438,
|
546 |
"speakers":5225552.0
|
547 |
},
|
548 |
{
|
549 |
"target_language_name":"Latgalian",
|
550 |
"bleu":56.4843556524,
|
551 |
+
"bert_score":0.9078494012,
|
552 |
"speakers":200000.0
|
553 |
},
|
554 |
+
{
|
555 |
+
"target_language_name":"Levantine Arabic",
|
556 |
+
"bleu":56.0898634013,
|
557 |
+
"bert_score":0.9437467565,
|
558 |
+
"speakers":44000000.0
|
559 |
+
},
|
560 |
{
|
561 |
"target_language_name":"Ligurian",
|
562 |
"bleu":55.8530636302,
|
563 |
+
"bert_score":0.9047620773,
|
564 |
"speakers":500000.0
|
565 |
},
|
566 |
{
|
567 |
"target_language_name":"Limburgish",
|
568 |
"bleu":59.4485504982,
|
569 |
+
"bert_score":0.8987095455,
|
570 |
"speakers":1600000.0
|
571 |
},
|
572 |
{
|
573 |
"target_language_name":"Lingala",
|
574 |
"bleu":30.4322896531,
|
575 |
+
"bert_score":0.8553236572,
|
576 |
"speakers":20000000.0
|
577 |
},
|
578 |
{
|
579 |
"target_language_name":"Lithuanian",
|
580 |
"bleu":67.1625695571,
|
581 |
+
"bert_score":0.9154702902,
|
582 |
"speakers":4000000.0
|
583 |
},
|
584 |
{
|
585 |
"target_language_name":"Lombard",
|
586 |
"bleu":46.3884402674,
|
587 |
+
"bert_score":0.8643471499,
|
588 |
"speakers":3900000.0
|
589 |
},
|
590 |
{
|
591 |
"target_language_name":"Luba-Kasai",
|
592 |
"bleu":45.0655291655,
|
593 |
+
"bert_score":0.8749240279,
|
594 |
"speakers":6300000.0
|
595 |
},
|
596 |
{
|
597 |
"target_language_name":"Luxembourgish",
|
598 |
"bleu":70.8338190438,
|
599 |
+
"bert_score":0.9297492107,
|
600 |
"speakers":391200.0
|
601 |
},
|
602 |
{
|
603 |
"target_language_name":"Macedonian",
|
604 |
"bleu":72.2733471437,
|
605 |
+
"bert_score":0.9558346649,
|
606 |
"speakers":2000000.0
|
607 |
},
|
608 |
{
|
609 |
"target_language_name":"Magahi",
|
610 |
"bleu":58.5474221546,
|
611 |
+
"bert_score":0.9458349566,
|
612 |
"speakers":20700000.0
|
613 |
},
|
614 |
{
|
615 |
"target_language_name":"Maithili",
|
616 |
"bleu":54.6530071391,
|
617 |
+
"bert_score":0.9433513383,
|
618 |
"speakers":33900000.0
|
619 |
},
|
620 |
{
|
621 |
"target_language_name":"Malayalam",
|
622 |
"bleu":64.0655894091,
|
623 |
+
"bert_score":0.9803075671,
|
624 |
"speakers":37100000.0
|
625 |
},
|
626 |
{
|
627 |
"target_language_name":"Maltese",
|
628 |
"bleu":80.0866777263,
|
629 |
+
"bert_score":0.9520254652,
|
630 |
"speakers":570000.0
|
631 |
},
|
632 |
+
{
|
633 |
+
"target_language_name":"Mandarin Chinese",
|
634 |
+
"bleu":42.5300166785,
|
635 |
+
"bert_score":0.9634857118,
|
636 |
+
"speakers":1074000000.0
|
637 |
+
},
|
638 |
{
|
639 |
"target_language_name":"Maori",
|
640 |
"bleu":54.8319935643,
|
641 |
+
"bert_score":0.9185245017,
|
642 |
"speakers":160000.0
|
643 |
},
|
644 |
{
|
645 |
"target_language_name":"Marathi",
|
646 |
"bleu":57.4434090711,
|
647 |
+
"bert_score":0.9421781262,
|
648 |
"speakers":83100000.0
|
649 |
},
|
650 |
+
{
|
651 |
+
"target_language_name":"Meadow Mari",
|
652 |
+
"bleu":49.7911680582,
|
653 |
+
"bert_score":0.9295116961,
|
654 |
+
"speakers":482000.0
|
655 |
+
},
|
656 |
{
|
657 |
"target_language_name":"Meitei",
|
658 |
"bleu":41.2619945571,
|
659 |
+
"bert_score":0.9528288851,
|
660 |
"speakers":1470000.0
|
661 |
},
|
662 |
+
{
|
663 |
+
"target_language_name":"Merina Malagasy",
|
664 |
+
"bleu":61.0968434546,
|
665 |
+
"bert_score":0.9032936792,
|
666 |
+
"speakers":0.0
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"target_language_name":"Mesopotamian Arabic",
|
670 |
+
"bleu":49.5184865297,
|
671 |
+
"bert_score":0.9382626355,
|
672 |
+
"speakers":15700000.0
|
673 |
+
},
|
674 |
{
|
675 |
"target_language_name":"Minangkabau",
|
676 |
"bleu":50.7407956197,
|
677 |
+
"bert_score":0.9252789746,
|
678 |
"speakers":5530000.0
|
679 |
},
|
680 |
{
|
681 |
"target_language_name":"Mizo",
|
682 |
"bleu":51.6558017488,
|
683 |
+
"bert_score":0.8875152906,
|
684 |
"speakers":500000.0
|
685 |
},
|
686 |
{
|
687 |
"target_language_name":"Moore",
|
688 |
"bleu":32.8458097983,
|
689 |
+
"bert_score":0.8583020627,
|
690 |
"speakers":7600000.0
|
691 |
},
|
692 |
+
{
|
693 |
+
"target_language_name":"Moroccan Arabic",
|
694 |
+
"bleu":49.3082976781,
|
695 |
+
"bert_score":0.9317501009,
|
696 |
+
"speakers":27500000.0
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"target_language_name":"Najdi Arabic",
|
700 |
+
"bleu":46.4102430377,
|
701 |
+
"bert_score":0.9332984229,
|
702 |
+
"speakers":0.0
|
703 |
+
},
|
704 |
{
|
705 |
"target_language_name":"Nepali",
|
706 |
"bleu":55.2919347352,
|
707 |
+
"bert_score":0.9358912428,
|
708 |
"speakers":0.0
|
709 |
},
|
710 |
+
{
|
711 |
+
"target_language_name":"Nigerian Fulfulde",
|
712 |
+
"bleu":28.1761055913,
|
713 |
+
"bert_score":0.8343587597,
|
714 |
+
"speakers":14500000.0
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"target_language_name":"North Azerbaijani",
|
718 |
+
"bleu":55.5265107063,
|
719 |
+
"bert_score":0.9145456314,
|
720 |
+
"speakers":9220610.0
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"target_language_name":"Northern Kurdish",
|
724 |
+
"bleu":55.7965878227,
|
725 |
+
"bert_score":0.9104436457,
|
726 |
+
"speakers":14600000.0
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"target_language_name":"Northern Sotho",
|
730 |
+
"bleu":62.8769401692,
|
731 |
+
"bert_score":0.9261207898,
|
732 |
+
"speakers":4100000.0
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"target_language_name":"Northern Uzbek",
|
736 |
+
"bleu":63.205573851,
|
737 |
+
"bert_score":0.9120756924,
|
738 |
+
"speakers":26912410.0
|
739 |
+
},
|
740 |
{
|
741 |
"target_language_name":"Nuer",
|
742 |
"bleu":16.5796987951,
|
743 |
+
"bert_score":0.8528214693,
|
744 |
"speakers":900000.0
|
745 |
},
|
746 |
{
|
747 |
"target_language_name":"N\u2019Ko",
|
748 |
"bleu":32.483490799,
|
749 |
+
"bert_score":0.9823745767,
|
750 |
"speakers":0.0
|
751 |
},
|
752 |
{
|
753 |
"target_language_name":"Occitan",
|
754 |
"bleu":71.532740184,
|
755 |
+
"bert_score":0.9337525626,
|
756 |
"speakers":542000.0
|
757 |
},
|
758 |
{
|
759 |
"target_language_name":"Odia",
|
760 |
"bleu":57.3628096518,
|
761 |
+
"bert_score":0.9768644154,
|
762 |
"speakers":34500000.0
|
763 |
},
|
764 |
{
|
765 |
"target_language_name":"Pangasinan",
|
766 |
"bleu":56.0048183827,
|
767 |
+
"bert_score":0.8906280657,
|
768 |
"speakers":1100000.0
|
769 |
},
|
770 |
{
|
771 |
"target_language_name":"Papiamentu",
|
772 |
"bleu":69.7955328133,
|
773 |
+
"bert_score":0.9325902323,
|
774 |
"speakers":321300.0
|
775 |
},
|
776 |
+
{
|
777 |
+
"target_language_name":"Paraguayan Guaran\u00ed",
|
778 |
+
"bleu":41.7929863707,
|
779 |
+
"bert_score":0.8764786462,
|
780 |
+
"speakers":0.0
|
781 |
+
},
|
782 |
{
|
783 |
"target_language_name":"Polish",
|
784 |
"bleu":61.8768399674,
|
785 |
+
"bert_score":0.9179250948,
|
786 |
"speakers":40200000.0
|
787 |
},
|
788 |
{
|
789 |
"target_language_name":"Portuguese",
|
790 |
"bleu":77.4978074222,
|
791 |
+
"bert_score":0.9494876027,
|
792 |
"speakers":254300000.0
|
793 |
},
|
794 |
{
|
795 |
"target_language_name":"Romanian",
|
796 |
"bleu":76.4907159035,
|
797 |
+
"bert_score":0.9455295324,
|
798 |
"speakers":24300000.0
|
799 |
},
|
800 |
{
|
801 |
"target_language_name":"Rundi",
|
802 |
"bleu":48.943513629,
|
803 |
+
"bert_score":0.8933652222,
|
804 |
"speakers":10800000.0
|
805 |
},
|
806 |
{
|
807 |
"target_language_name":"Russian",
|
808 |
"bleu":71.1489441039,
|
809 |
+
"bert_score":0.9518508852,
|
810 |
"speakers":171428900.0
|
811 |
},
|
812 |
{
|
813 |
"target_language_name":"Samoan",
|
814 |
"bleu":56.7138831423,
|
815 |
+
"bert_score":0.9166683555,
|
816 |
"speakers":415720.0
|
817 |
},
|
818 |
{
|
819 |
"target_language_name":"Sango",
|
820 |
"bleu":34.8754222657,
|
821 |
+
"bert_score":0.8720244229,
|
822 |
"speakers":4600000.0
|
823 |
},
|
824 |
{
|
825 |
"target_language_name":"Sanskrit",
|
826 |
"bleu":32.7813249911,
|
827 |
+
"bert_score":0.8987655501,
|
828 |
"speakers":49736.0
|
829 |
},
|
830 |
{
|
831 |
"target_language_name":"Santhali",
|
832 |
"bleu":31.5119247269,
|
833 |
+
"bert_score":0.944095705,
|
834 |
"speakers":7200000.0
|
835 |
},
|
836 |
{
|
837 |
"target_language_name":"Sardinian",
|
838 |
"bleu":62.6903914771,
|
839 |
+
"bert_score":0.9118991812,
|
840 |
"speakers":1300000.0
|
841 |
},
|
842 |
{
|
843 |
"target_language_name":"Scottish Gaelic",
|
844 |
"bleu":62.6044371338,
|
845 |
+
"bert_score":0.9264988482,
|
846 |
"speakers":60130.0
|
847 |
},
|
848 |
{
|
849 |
"target_language_name":"Serbian",
|
850 |
"bleu":69.9691396176,
|
851 |
+
"bert_score":0.9582955678,
|
852 |
"speakers":9000000.0
|
853 |
},
|
854 |
{
|
855 |
"target_language_name":"Setswana",
|
856 |
"bleu":55.2288890228,
|
857 |
+
"bert_score":0.9117900888,
|
858 |
"speakers":4500000.0
|
859 |
},
|
860 |
{
|
861 |
"target_language_name":"Shan",
|
862 |
"bleu":29.2129948577,
|
863 |
+
"bert_score":0.9378574808,
|
864 |
"speakers":3000000.0
|
865 |
},
|
866 |
{
|
867 |
"target_language_name":"Shona",
|
868 |
"bleu":51.5592191405,
|
869 |
+
"bert_score":0.8798740129,
|
870 |
"speakers":9023000.0
|
871 |
},
|
872 |
{
|
873 |
"target_language_name":"Sicilian",
|
874 |
"bleu":58.5895359443,
|
875 |
+
"bert_score":0.90428345,
|
876 |
"speakers":4700000.0
|
877 |
},
|
878 |
{
|
879 |
"target_language_name":"Silesian",
|
880 |
"bleu":56.7836392069,
|
881 |
+
"bert_score":0.9106028736,
|
882 |
"speakers":522000.0
|
883 |
},
|
884 |
{
|
885 |
"target_language_name":"Sindhi",
|
886 |
"bleu":48.1876056648,
|
887 |
+
"bert_score":0.936702015,
|
888 |
"speakers":25000000.0
|
889 |
},
|
890 |
{
|
891 |
"target_language_name":"Sinhala",
|
892 |
"bleu":56.7567311796,
|
893 |
+
"bert_score":0.9713358581,
|
894 |
"speakers":15300000.0
|
895 |
},
|
896 |
{
|
897 |
"target_language_name":"Slovak",
|
898 |
"bleu":67.9284804086,
|
899 |
+
"bert_score":0.9360236605,
|
900 |
"speakers":6000000.0
|
901 |
},
|
902 |
{
|
903 |
"target_language_name":"Slovene",
|
904 |
"bleu":72.5691270757,
|
905 |
+
"bert_score":0.9432346245,
|
906 |
"speakers":2400000.0
|
907 |
},
|
908 |
{
|
909 |
"target_language_name":"Somali",
|
910 |
"bleu":55.3706496473,
|
911 |
+
"bert_score":0.908571593,
|
912 |
"speakers":16200000.0
|
913 |
},
|
914 |
+
{
|
915 |
+
"target_language_name":"South Azerbaijani",
|
916 |
+
"bleu":44.3712804302,
|
917 |
+
"bert_score":0.9420697371,
|
918 |
+
"speakers":15000000.0
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"target_language_name":"Southern Pashto",
|
922 |
+
"bleu":38.3124819374,
|
923 |
+
"bert_score":0.921268179,
|
924 |
+
"speakers":10900000.0
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"target_language_name":"Southern Sotho",
|
928 |
+
"bleu":56.735299554,
|
929 |
+
"bert_score":0.9102749407,
|
930 |
+
"speakers":6000000.0
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"target_language_name":"Southwestern Dinka",
|
934 |
+
"bleu":17.5913281403,
|
935 |
+
"bert_score":0.8016291638,
|
936 |
+
"speakers":0.0
|
937 |
+
},
|
938 |
{
|
939 |
"target_language_name":"Spanish",
|
940 |
"bleu":63.8467073379,
|
941 |
+
"bert_score":0.9224406302,
|
942 |
"speakers":485000000.0
|
943 |
},
|
944 |
+
{
|
945 |
+
"target_language_name":"Standard Arabic",
|
946 |
+
"bleu":56.8831262708,
|
947 |
+
"bert_score":0.9168330083,
|
948 |
+
"speakers":0.0
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"target_language_name":"Standard Estonian",
|
952 |
+
"bleu":67.4156919517,
|
953 |
+
"bert_score":0.9277306815,
|
954 |
+
"speakers":1164770.0
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"target_language_name":"Standard German",
|
958 |
+
"bleu":77.1966515107,
|
959 |
+
"bert_score":0.9468763133,
|
960 |
+
"speakers":105000000.0
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"target_language_name":"Standard Latvian",
|
964 |
+
"bleu":65.0833210037,
|
965 |
+
"bert_score":0.9217625757,
|
966 |
+
"speakers":0.0
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"target_language_name":"Standard Malay",
|
970 |
+
"bleu":74.2657232798,
|
971 |
+
"bert_score":0.9445500493,
|
972 |
+
"speakers":0.0
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"target_language_name":"Standard Moroccan Tamazight",
|
976 |
+
"bleu":35.6247648109,
|
977 |
+
"bert_score":0.9847298423,
|
978 |
+
"speakers":0.0
|
979 |
+
},
|
980 |
{
|
981 |
"target_language_name":"Sunda",
|
982 |
"bleu":56.4065999104,
|
983 |
+
"bert_score":0.9077177823,
|
984 |
"speakers":32400000.0
|
985 |
},
|
986 |
{
|
987 |
"target_language_name":"Swahili",
|
988 |
"bleu":73.5199042142,
|
989 |
+
"bert_score":0.9450787365,
|
990 |
"speakers":82300000.0
|
991 |
},
|
992 |
{
|
993 |
"target_language_name":"Swati",
|
994 |
"bleu":52.7746096439,
|
995 |
+
"bert_score":0.8899940272,
|
996 |
"speakers":2034200.0
|
997 |
},
|
998 |
{
|
999 |
"target_language_name":"Swedish",
|
1000 |
"bleu":77.421610247,
|
1001 |
+
"bert_score":0.9571870168,
|
1002 |
"speakers":9244250.0
|
1003 |
},
|
1004 |
{
|
1005 |
"target_language_name":"Tajik",
|
1006 |
"bleu":60.9783684158,
|
1007 |
+
"bert_score":0.9378365338,
|
1008 |
"speakers":14000000.0
|
1009 |
},
|
1010 |
{
|
1011 |
"target_language_name":"Tamasheq",
|
1012 |
"bleu":18.4319889721,
|
1013 |
+
"bert_score":0.8427422295,
|
1014 |
"speakers":500000.0
|
1015 |
},
|
1016 |
{
|
1017 |
"target_language_name":"Tamil",
|
1018 |
"bleu":65.7863221054,
|
1019 |
+
"bert_score":0.9536473691,
|
1020 |
"speakers":75000000.0
|
1021 |
},
|
1022 |
{
|
1023 |
"target_language_name":"Tatar",
|
1024 |
"bleu":60.3447467213,
|
1025 |
+
"bert_score":0.9364115715,
|
1026 |
"speakers":5427318.0
|
1027 |
},
|
1028 |
+
{
|
1029 |
+
"target_language_name":"Ta\u2019izzi-Adeni Arabic",
|
1030 |
+
"bleu":49.4139335281,
|
1031 |
+
"bert_score":0.9354432185,
|
1032 |
+
"speakers":10500000.0
|
1033 |
+
},
|
1034 |
{
|
1035 |
"target_language_name":"Telugu",
|
1036 |
"bleu":61.6352457629,
|
1037 |
+
"bert_score":0.9790697515,
|
1038 |
"speakers":82000000.0
|
1039 |
},
|
1040 |
{
|
1041 |
"target_language_name":"Thai",
|
1042 |
"bleu":62.8125360944,
|
1043 |
+
"bert_score":0.9225328485,
|
1044 |
"speakers":40000000.0
|
1045 |
},
|
1046 |
{
|
1047 |
"target_language_name":"Tigrigna",
|
1048 |
"bleu":32.8711961703,
|
1049 |
+
"bert_score":0.9852415164,
|
1050 |
"speakers":7507780.0
|
1051 |
},
|
1052 |
{
|
1053 |
"target_language_name":"Tok Pisin",
|
1054 |
"bleu":56.5407760367,
|
1055 |
+
"bert_score":0.9031182428,
|
1056 |
"speakers":4000000.0
|
1057 |
},
|
1058 |
+
{
|
1059 |
+
"target_language_name":"Tosk Albanian",
|
1060 |
+
"bleu":69.4218765092,
|
1061 |
+
"bert_score":0.9402680953,
|
1062 |
+
"speakers":3000000.0
|
1063 |
+
},
|
1064 |
{
|
1065 |
"target_language_name":"Tsonga",
|
1066 |
"bleu":58.3516573597,
|
1067 |
+
"bert_score":0.9134832978,
|
1068 |
"speakers":13000000.0
|
1069 |
},
|
1070 |
{
|
1071 |
"target_language_name":"Tumbuka",
|
1072 |
"bleu":44.0490017392,
|
1073 |
+
"bert_score":0.8865564326,
|
1074 |
"speakers":2680000.0
|
1075 |
},
|
1076 |
+
{
|
1077 |
+
"target_language_name":"Tunisian Arabic",
|
1078 |
+
"bleu":49.6714090744,
|
1079 |
+
"bert_score":0.9337966998,
|
1080 |
+
"speakers":11600000.0
|
1081 |
+
},
|
1082 |
{
|
1083 |
"target_language_name":"Turkish",
|
1084 |
"bleu":67.1600625676,
|
1085 |
+
"bert_score":0.9309494158,
|
1086 |
"speakers":82231620.0
|
1087 |
},
|
1088 |
{
|
1089 |
"target_language_name":"Turkmen",
|
1090 |
"bleu":60.5593705936,
|
1091 |
+
"bert_score":0.9125106474,
|
1092 |
"speakers":16000000.0
|
1093 |
},
|
1094 |
{
|
1095 |
"target_language_name":"Twi",
|
1096 |
"bleu":44.7976562068,
|
1097 |
+
"bert_score":0.8913615406,
|
1098 |
"speakers":3000000.0
|
1099 |
},
|
1100 |
{
|
1101 |
"target_language_name":"Ukrainian",
|
1102 |
"bleu":68.0976232544,
|
1103 |
+
"bert_score":0.9468558848,
|
1104 |
"speakers":34710100.0
|
1105 |
},
|
1106 |
{
|
1107 |
"target_language_name":"Umbundu",
|
1108 |
"bleu":21.0802775597,
|
1109 |
+
"bert_score":0.8461364289,
|
1110 |
"speakers":6000000.0
|
1111 |
},
|
1112 |
{
|
1113 |
"target_language_name":"Urdu",
|
1114 |
"bleu":61.1255457272,
|
1115 |
+
"bert_score":0.953888009,
|
1116 |
"speakers":94022900.0
|
1117 |
},
|
1118 |
{
|
1119 |
"target_language_name":"Uyghur",
|
1120 |
"bleu":53.5346877103,
|
1121 |
+
"bert_score":0.9397906005,
|
1122 |
"speakers":10400000.0
|
1123 |
},
|
1124 |
{
|
1125 |
"target_language_name":"Venetian",
|
1126 |
"bleu":60.6140876271,
|
1127 |
+
"bert_score":0.9080212533,
|
1128 |
"speakers":2000000.0
|
1129 |
},
|
1130 |
{
|
1131 |
"target_language_name":"Vietnamese",
|
1132 |
"bleu":70.3560749464,
|
1133 |
+
"bert_score":0.9527418713,
|
1134 |
"speakers":76000000.0
|
1135 |
},
|
1136 |
{
|
1137 |
"target_language_name":"Waray-Waray",
|
1138 |
"bleu":66.3850231243,
|
1139 |
+
"bert_score":0.920412008,
|
1140 |
"speakers":3100000.0
|
1141 |
},
|
1142 |
{
|
1143 |
"target_language_name":"Welsh",
|
1144 |
"bleu":83.3437724474,
|
1145 |
+
"bert_score":0.9662299534,
|
1146 |
"speakers":977366.0
|
1147 |
},
|
1148 |
+
{
|
1149 |
+
"target_language_name":"West Central Oromo",
|
1150 |
+
"bleu":46.9090350028,
|
1151 |
+
"bert_score":0.8845542371,
|
1152 |
+
"speakers":0.0
|
1153 |
+
},
|
1154 |
{
|
1155 |
"target_language_name":"Wolof",
|
1156 |
"bleu":42.6430127569,
|
1157 |
+
"bert_score":0.8762976408,
|
1158 |
"speakers":3700000.0
|
1159 |
},
|
1160 |
{
|
1161 |
"target_language_name":"Xhosa",
|
1162 |
"bleu":55.4688091009,
|
1163 |
+
"bert_score":0.9008744816,
|
1164 |
"speakers":11000000.0
|
1165 |
},
|
1166 |
+
{
|
1167 |
+
"target_language_name":"Yerwa Kanuri",
|
1168 |
+
"bleu":18.5081787556,
|
1169 |
+
"bert_score":0.839997381,
|
1170 |
+
"speakers":0.0
|
1171 |
+
},
|
1172 |
{
|
1173 |
"target_language_name":"Yoruba",
|
1174 |
"bleu":34.2642542268,
|
1175 |
+
"bert_score":0.9001545012,
|
1176 |
"speakers":40000000.0
|
1177 |
},
|
1178 |
+
{
|
1179 |
+
"target_language_name":"Yue Chinese",
|
1180 |
+
"bleu":34.5614651228,
|
1181 |
+
"bert_score":0.9634495397,
|
1182 |
+
"speakers":73100000.0
|
1183 |
+
},
|
1184 |
{
|
1185 |
"target_language_name":"Zulu",
|
1186 |
"bleu":59.1762078389,
|
1187 |
+
"bert_score":0.9099391103,
|
1188 |
"speakers":15700000.0
|
1189 |
},
|
1190 |
{
|
1191 |
"target_language_name":"nno",
|
1192 |
"bleu":71.8615646296,
|
1193 |
+
"bert_score":0.9335320314,
|
1194 |
"speakers":0.0
|
1195 |
},
|
1196 |
{
|
1197 |
"target_language_name":"\u00c9w\u00e9",
|
1198 |
"bleu":41.6614038791,
|
1199 |
+
"bert_score":0.8829316159,
|
1200 |
"speakers":3000000.0
|
1201 |
}
|
1202 |
]
|
uv.lock
CHANGED
The diff for this file is too large to render.
See raw diff
|
|