update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- wer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: libri-alpha-0.85-Temp-1-processor-change
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# libri-alpha-0.85-Temp-1-processor-change
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 78.4467
|
| 19 |
+
- Wer: 0.1153
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 32
|
| 40 |
+
- eval_batch_size: 32
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 64
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 500
|
| 47 |
+
- num_epochs: 30
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
+
| 493.9213 | 0.75 | 100 | 145.7981 | 0.1515 |
|
| 55 |
+
| 410.8468 | 1.49 | 200 | 119.1579 | 0.1498 |
|
| 56 |
+
| 368.5187 | 2.24 | 300 | 109.7572 | 0.1505 |
|
| 57 |
+
| 329.7762 | 2.99 | 400 | 99.2350 | 0.1439 |
|
| 58 |
+
| 323.7352 | 3.73 | 500 | 92.1173 | 0.1356 |
|
| 59 |
+
| 305.1129 | 4.48 | 600 | 89.3685 | 0.1314 |
|
| 60 |
+
| 294.2529 | 5.22 | 700 | 88.3937 | 0.1287 |
|
| 61 |
+
| 284.5355 | 5.97 | 800 | 87.0589 | 0.1292 |
|
| 62 |
+
| 284.2181 | 6.72 | 900 | 86.4474 | 0.1298 |
|
| 63 |
+
| 273.915 | 7.46 | 1000 | 84.6149 | 0.1265 |
|
| 64 |
+
| 267.7668 | 8.21 | 1100 | 84.1840 | 0.1264 |
|
| 65 |
+
| 262.1592 | 8.96 | 1200 | 83.8678 | 0.1253 |
|
| 66 |
+
| 262.5562 | 9.7 | 1300 | 83.2756 | 0.1207 |
|
| 67 |
+
| 262.9982 | 10.45 | 1400 | 81.8095 | 0.1218 |
|
| 68 |
+
| 256.2891 | 11.19 | 1500 | 82.1241 | 0.1204 |
|
| 69 |
+
| 251.4134 | 11.94 | 1600 | 80.8432 | 0.1207 |
|
| 70 |
+
| 250.0854 | 12.69 | 1700 | 81.1467 | 0.1203 |
|
| 71 |
+
| 250.0077 | 13.43 | 1800 | 80.9370 | 0.1196 |
|
| 72 |
+
| 239.0915 | 14.18 | 1900 | 80.5060 | 0.1201 |
|
| 73 |
+
| 240.9192 | 14.93 | 2000 | 80.4557 | 0.1190 |
|
| 74 |
+
| 241.1668 | 15.67 | 2100 | 80.6453 | 0.1203 |
|
| 75 |
+
| 244.9744 | 16.42 | 2200 | 80.0101 | 0.1192 |
|
| 76 |
+
| 232.4748 | 17.16 | 2300 | 79.4798 | 0.1170 |
|
| 77 |
+
| 237.3503 | 17.91 | 2400 | 79.5743 | 0.1175 |
|
| 78 |
+
| 237.9698 | 18.66 | 2500 | 79.3368 | 0.1178 |
|
| 79 |
+
| 235.8808 | 19.4 | 2600 | 79.5519 | 0.1174 |
|
| 80 |
+
| 230.8314 | 20.15 | 2700 | 79.0367 | 0.1166 |
|
| 81 |
+
| 229.5856 | 20.9 | 2800 | 79.1809 | 0.1172 |
|
| 82 |
+
| 233.1034 | 21.64 | 2900 | 78.9896 | 0.1167 |
|
| 83 |
+
| 231.6986 | 22.39 | 3000 | 78.7184 | 0.1154 |
|
| 84 |
+
| 222.0106 | 23.13 | 3100 | 78.7308 | 0.1160 |
|
| 85 |
+
| 225.1484 | 23.88 | 3200 | 78.6649 | 0.1159 |
|
| 86 |
+
| 232.4254 | 24.63 | 3300 | 78.5096 | 0.1154 |
|
| 87 |
+
| 230.9492 | 25.37 | 3400 | 78.4873 | 0.1153 |
|
| 88 |
+
| 228.3062 | 26.12 | 3500 | 78.5155 | 0.1147 |
|
| 89 |
+
| 225.5572 | 26.87 | 3600 | 78.5693 | 0.1148 |
|
| 90 |
+
| 227.7358 | 27.61 | 3700 | 78.5487 | 0.1149 |
|
| 91 |
+
| 221.2486 | 28.36 | 3800 | 78.4307 | 0.1151 |
|
| 92 |
+
| 231.5915 | 29.1 | 3900 | 78.4270 | 0.1153 |
|
| 93 |
+
| 231.7214 | 29.85 | 4000 | 78.4467 | 0.1153 |
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
### Framework versions
|
| 97 |
+
|
| 98 |
+
- Transformers 4.25.1
|
| 99 |
+
- Pytorch 1.12.1
|
| 100 |
+
- Datasets 2.7.1
|
| 101 |
+
- Tokenizers 0.11.0
|