update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Model_S_D_Wav2Vec2
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# Model_S_D_Wav2Vec2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0464
|
| 21 |
+
- Wer: 0.2319
|
| 22 |
+
- Cer: 0.0598
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0003
|
| 42 |
+
- train_batch_size: 16
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 500
|
| 50 |
+
- num_epochs: 30
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
|
| 56 |
+
| 3.5768 | 0.85 | 400 | 0.6152 | 0.5812 | 0.1905 |
|
| 57 |
+
| 0.3226 | 1.71 | 800 | 0.1026 | 0.3195 | 0.0722 |
|
| 58 |
+
| 0.1827 | 2.56 | 1200 | 0.0725 | 0.2048 | 0.0454 |
|
| 59 |
+
| 0.129 | 3.41 | 1600 | 0.0671 | 0.2393 | 0.0525 |
|
| 60 |
+
| 0.1075 | 4.26 | 2000 | 0.0556 | 0.2312 | 0.0497 |
|
| 61 |
+
| 0.0924 | 5.12 | 2400 | 0.0572 | 0.2040 | 0.0478 |
|
| 62 |
+
| 0.076 | 5.97 | 2800 | 0.0596 | 0.1472 | 0.0346 |
|
| 63 |
+
| 0.0695 | 6.82 | 3200 | 0.0608 | 0.2274 | 0.0510 |
|
| 64 |
+
| 0.0707 | 7.68 | 3600 | 0.0490 | 0.2665 | 0.0660 |
|
| 65 |
+
| 0.0597 | 8.53 | 4000 | 0.0509 | 0.2442 | 0.0593 |
|
| 66 |
+
| 0.0557 | 9.38 | 4400 | 0.0501 | 0.2533 | 0.0610 |
|
| 67 |
+
| 0.0503 | 10.23 | 4800 | 0.0519 | 0.2534 | 0.0622 |
|
| 68 |
+
| 0.0471 | 11.09 | 5200 | 0.0512 | 0.2585 | 0.0638 |
|
| 69 |
+
| 0.0417 | 11.94 | 5600 | 0.0497 | 0.2522 | 0.0610 |
|
| 70 |
+
| 0.0415 | 12.79 | 6000 | 0.0508 | 0.2547 | 0.0629 |
|
| 71 |
+
| 0.0372 | 13.65 | 6400 | 0.0497 | 0.2580 | 0.0643 |
|
| 72 |
+
| 0.0364 | 14.5 | 6800 | 0.0448 | 0.2498 | 0.0600 |
|
| 73 |
+
| 0.034 | 15.35 | 7200 | 0.0522 | 0.2419 | 0.0593 |
|
| 74 |
+
| 0.0306 | 16.2 | 7600 | 0.0510 | 0.2433 | 0.0560 |
|
| 75 |
+
| 0.0345 | 17.06 | 8000 | 0.0503 | 0.2610 | 0.0657 |
|
| 76 |
+
| 0.0266 | 17.91 | 8400 | 0.0462 | 0.2434 | 0.0620 |
|
| 77 |
+
| 0.0273 | 18.76 | 8800 | 0.0507 | 0.2456 | 0.0622 |
|
| 78 |
+
| 0.0216 | 19.62 | 9200 | 0.0466 | 0.2214 | 0.0531 |
|
| 79 |
+
| 0.0208 | 20.47 | 9600 | 0.0497 | 0.2396 | 0.0598 |
|
| 80 |
+
| 0.0201 | 21.32 | 10000 | 0.0470 | 0.2332 | 0.0559 |
|
| 81 |
+
| 0.0174 | 22.17 | 10400 | 0.0418 | 0.2346 | 0.0590 |
|
| 82 |
+
| 0.0198 | 23.03 | 10800 | 0.0472 | 0.2386 | 0.0602 |
|
| 83 |
+
| 0.0149 | 23.88 | 11200 | 0.0490 | 0.2446 | 0.0638 |
|
| 84 |
+
| 0.0133 | 24.73 | 11600 | 0.0497 | 0.2430 | 0.0632 |
|
| 85 |
+
| 0.0118 | 25.59 | 12000 | 0.0498 | 0.2368 | 0.0620 |
|
| 86 |
+
| 0.0106 | 26.44 | 12400 | 0.0453 | 0.2309 | 0.0590 |
|
| 87 |
+
| 0.0104 | 27.29 | 12800 | 0.0452 | 0.2296 | 0.0583 |
|
| 88 |
+
| 0.0085 | 28.14 | 13200 | 0.0467 | 0.2352 | 0.0604 |
|
| 89 |
+
| 0.0081 | 29.0 | 13600 | 0.0470 | 0.2310 | 0.0592 |
|
| 90 |
+
| 0.0079 | 29.85 | 14000 | 0.0464 | 0.2319 | 0.0598 |
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
### Framework versions
|
| 94 |
+
|
| 95 |
+
- Transformers 4.31.0
|
| 96 |
+
- Pytorch 2.0.1+cu117
|
| 97 |
+
- Datasets 1.18.3
|
| 98 |
+
- Tokenizers 0.13.3
|