Fine-tuning in progress
Browse files- README.md +21 -8
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: Whisper-Large-v3-turbo-STT-Zeroth-KO-v2
|
| 7 |
results: []
|
|
@@ -14,14 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model was trained from scratch on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
-
|
| 18 |
-
-
|
| 19 |
-
-
|
| 20 |
-
- eval_runtime: 241.0372
|
| 21 |
-
- eval_samples_per_second: 2.97
|
| 22 |
-
- eval_steps_per_second: 0.373
|
| 23 |
-
- epoch: 1.0513
|
| 24 |
-
- step: 5000
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -49,6 +46,22 @@ The following hyperparameters were used during training:
|
|
| 49 |
- lr_scheduler_warmup_steps: 100
|
| 50 |
- training_steps: 5000
|
| 51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
### Framework versions
|
| 53 |
|
| 54 |
- Transformers 4.48.2
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
model-index:
|
| 8 |
- name: Whisper-Large-v3-turbo-STT-Zeroth-KO-v2
|
| 9 |
results: []
|
|
|
|
| 16 |
|
| 17 |
This model was trained from scratch on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0169
|
| 20 |
+
- Wer: 23.9851
|
| 21 |
+
- Cer: 0.0904
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 46 |
- lr_scheduler_warmup_steps: 100
|
| 47 |
- training_steps: 5000
|
| 48 |
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:------:|:----:|:------:|:---------------:|:-------:|
|
| 53 |
+
| 0.2413 | 0.1051 | 500 | 0.0771 | 0.0187 | 23.3663 |
|
| 54 |
+
| 0.0191 | 0.2103 | 1000 | 0.0959 | 0.0174 | 26.5347 |
|
| 55 |
+
| 0.0187 | 0.3154 | 1500 | 0.0916 | 0.0171 | 24.1213 |
|
| 56 |
+
| 0.0171 | 0.4205 | 2000 | 0.0882 | 0.0171 | 23.6757 |
|
| 57 |
+
| 0.018 | 0.5257 | 2500 | 0.0876 | 0.0170 | 23.4035 |
|
| 58 |
+
| 0.0173 | 0.6308 | 3000 | 0.0878 | 0.0171 | 23.5396 |
|
| 59 |
+
| 0.0179 | 0.7359 | 3500 | 0.0170 | 23.8366 | 0.0902 |
|
| 60 |
+
| 0.0189 | 0.8410 | 4000 | 0.0169 | 23.4406 | 0.0873 |
|
| 61 |
+
| 0.0172 | 0.9462 | 4500 | 0.0169 | 24.0594 | 0.0914 |
|
| 62 |
+
| 0.0164 | 1.0513 | 5000 | 0.0169 | 23.9851 | 0.0904 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
### Framework versions
|
| 66 |
|
| 67 |
- Transformers 4.48.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1617828008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fe9907c94f3656a9e9d5855bde410aa7e1c12e976acc3cd5323cd6c4edb93b5
|
| 3 |
size 1617828008
|