|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-xls-r-300m |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: wav2vec2-E30_speed3 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# wav2vec2-E30_speed3 |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2614 |
|
- Cer: 27.0035 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 50 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer | |
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
| 44.2054 | 0.1289 | 200 | 5.4975 | 100.0 | |
|
| 5.0916 | 0.2579 | 400 | 4.7077 | 100.0 | |
|
| 4.8758 | 0.3868 | 600 | 4.6568 | 100.0 | |
|
| 4.8539 | 0.5158 | 800 | 4.6120 | 100.0 | |
|
| 4.7493 | 0.6447 | 1000 | 4.5950 | 100.0 | |
|
| 4.5763 | 0.7737 | 1200 | 4.3522 | 98.5076 | |
|
| 3.7522 | 0.9026 | 1400 | 3.0023 | 54.3478 | |
|
| 2.71 | 1.0316 | 1600 | 2.6582 | 48.0200 | |
|
| 2.3514 | 1.1605 | 1800 | 2.3269 | 42.1034 | |
|
| 1.9845 | 1.2895 | 2000 | 1.9847 | 36.9918 | |
|
| 1.7755 | 1.4184 | 2200 | 1.8688 | 35.3643 | |
|
| 1.6234 | 1.5474 | 2400 | 1.7565 | 33.8837 | |
|
| 1.5417 | 1.6763 | 2600 | 1.7060 | 33.1199 | |
|
| 1.4338 | 1.8053 | 2800 | 1.6633 | 33.5194 | |
|
| 1.3403 | 1.9342 | 3000 | 1.5921 | 32.7791 | |
|
| 1.2466 | 2.0632 | 3200 | 1.5050 | 31.0458 | |
|
| 1.1278 | 2.1921 | 3400 | 1.4261 | 29.5828 | |
|
| 1.0863 | 2.3211 | 3600 | 1.3675 | 28.9189 | |
|
| 1.0236 | 2.4500 | 3800 | 1.3119 | 27.9318 | |
|
| 0.9973 | 2.5790 | 4000 | 1.2762 | 27.2150 | |
|
| 0.9749 | 2.7079 | 4200 | 1.3005 | 27.4677 | |
|
| 0.9365 | 2.8369 | 4400 | 1.2889 | 27.6204 | |
|
| 0.8997 | 2.9658 | 4600 | 1.2614 | 27.0035 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.2 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
