update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-large-xlsr-53-torgo-demo-f01-nolm
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# wav2vec2-large-xlsr-53-torgo-demo-f01-nolm
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.0153
|
| 18 |
+
- Wer: 0.4756
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 500
|
| 44 |
+
- num_epochs: 30
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 51 |
+
| 3.4166 | 0.81 | 500 | 4.5019 | 1.0 |
|
| 52 |
+
| 3.1088 | 1.62 | 1000 | 3.0459 | 1.0 |
|
| 53 |
+
| 2.8249 | 2.44 | 1500 | 3.0850 | 1.0 |
|
| 54 |
+
| 2.625 | 3.25 | 2000 | 2.6827 | 1.3656 |
|
| 55 |
+
| 1.9816 | 4.06 | 2500 | 1.6636 | 1.3701 |
|
| 56 |
+
| 1.3036 | 4.87 | 3000 | 0.9710 | 1.2504 |
|
| 57 |
+
| 0.9862 | 5.68 | 3500 | 0.6023 | 1.0519 |
|
| 58 |
+
| 0.7012 | 6.49 | 4000 | 0.4404 | 0.9342 |
|
| 59 |
+
| 0.6102 | 7.31 | 4500 | 0.3297 | 0.8491 |
|
| 60 |
+
| 0.5463 | 8.12 | 5000 | 0.2403 | 0.7773 |
|
| 61 |
+
| 0.4897 | 8.93 | 5500 | 0.1907 | 0.7335 |
|
| 62 |
+
| 0.4687 | 9.74 | 6000 | 0.1721 | 0.7095 |
|
| 63 |
+
| 0.41 | 10.55 | 6500 | 0.1382 | 0.6851 |
|
| 64 |
+
| 0.3277 | 11.36 | 7000 | 0.1189 | 0.6598 |
|
| 65 |
+
| 0.3182 | 12.18 | 7500 | 0.1040 | 0.6372 |
|
| 66 |
+
| 0.3279 | 12.99 | 8000 | 0.0961 | 0.6274 |
|
| 67 |
+
| 0.2735 | 13.8 | 8500 | 0.0806 | 0.5880 |
|
| 68 |
+
| 0.3153 | 14.61 | 9000 | 0.0821 | 0.5748 |
|
| 69 |
+
| 0.251 | 15.42 | 9500 | 0.0633 | 0.5437 |
|
| 70 |
+
| 0.2 | 16.23 | 10000 | 0.0534 | 0.5316 |
|
| 71 |
+
| 0.2134 | 17.05 | 10500 | 0.0475 | 0.5195 |
|
| 72 |
+
| 0.1727 | 17.86 | 11000 | 0.0435 | 0.5146 |
|
| 73 |
+
| 0.2143 | 18.67 | 11500 | 0.0406 | 0.5072 |
|
| 74 |
+
| 0.1679 | 19.48 | 12000 | 0.0386 | 0.5057 |
|
| 75 |
+
| 0.1836 | 20.29 | 12500 | 0.0359 | 0.4984 |
|
| 76 |
+
| 0.1542 | 21.1 | 13000 | 0.0284 | 0.4914 |
|
| 77 |
+
| 0.1672 | 21.92 | 13500 | 0.0289 | 0.4884 |
|
| 78 |
+
| 0.1526 | 22.73 | 14000 | 0.0256 | 0.4867 |
|
| 79 |
+
| 0.1263 | 23.54 | 14500 | 0.0247 | 0.4871 |
|
| 80 |
+
| 0.133 | 24.35 | 15000 | 0.0194 | 0.4816 |
|
| 81 |
+
| 0.1005 | 25.16 | 15500 | 0.0190 | 0.4798 |
|
| 82 |
+
| 0.1372 | 25.97 | 16000 | 0.0172 | 0.4786 |
|
| 83 |
+
| 0.1126 | 26.79 | 16500 | 0.0177 | 0.4773 |
|
| 84 |
+
| 0.0929 | 27.6 | 17000 | 0.0173 | 0.4775 |
|
| 85 |
+
| 0.1069 | 28.41 | 17500 | 0.0164 | 0.4773 |
|
| 86 |
+
| 0.0932 | 29.22 | 18000 | 0.0153 | 0.4756 |
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
### Framework versions
|
| 90 |
+
|
| 91 |
+
- Transformers 4.23.1
|
| 92 |
+
- Pytorch 1.12.1+cu113
|
| 93 |
+
- Datasets 2.0.0
|
| 94 |
+
- Tokenizers 0.13.2
|