|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: wav2vec2-3 |
|
|
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. --> |
|
|
|
|
|
# wav2vec2-3 |
|
|
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.1124 |
|
|
- Wer: 1.0 |
|
|
|
|
|
## 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: 0.001 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 400 |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:---:| |
|
|
| 3.7797 | 0.34 | 200 | 3.0703 | 1.0 | |
|
|
| 2.8701 | 0.69 | 400 | 3.3128 | 1.0 | |
|
|
| 2.8695 | 1.03 | 600 | 3.1333 | 1.0 | |
|
|
| 2.8634 | 1.38 | 800 | 3.1634 | 1.0 | |
|
|
| 2.8629 | 1.72 | 1000 | 3.0432 | 1.0 | |
|
|
| 2.8652 | 2.07 | 1200 | 3.0300 | 1.0 | |
|
|
| 2.8602 | 2.41 | 1400 | 3.1894 | 1.0 | |
|
|
| 2.8622 | 2.75 | 1600 | 3.1950 | 1.0 | |
|
|
| 2.8606 | 3.1 | 1800 | 3.0656 | 1.0 | |
|
|
| 2.8605 | 3.44 | 2000 | 3.0614 | 1.0 | |
|
|
| 2.8595 | 3.79 | 2200 | 3.0697 | 1.0 | |
|
|
| 2.8504 | 4.13 | 2400 | 3.1404 | 1.0 | |
|
|
| 2.8553 | 4.48 | 2600 | 3.0682 | 1.0 | |
|
|
| 2.8585 | 4.82 | 2800 | 3.1393 | 1.0 | |
|
|
| 2.8567 | 5.16 | 3000 | 3.1013 | 1.0 | |
|
|
| 2.8539 | 5.51 | 3200 | 3.0740 | 1.0 | |
|
|
| 2.8588 | 5.85 | 3400 | 3.0616 | 1.0 | |
|
|
| 2.8509 | 6.2 | 3600 | 3.1032 | 1.0 | |
|
|
| 2.8589 | 6.54 | 3800 | 3.1348 | 1.0 | |
|
|
| 2.8505 | 6.88 | 4000 | 3.1514 | 1.0 | |
|
|
| 2.8548 | 7.23 | 4200 | 3.1319 | 1.0 | |
|
|
| 2.8466 | 7.57 | 4400 | 3.1412 | 1.0 | |
|
|
| 2.8549 | 7.92 | 4600 | 3.1235 | 1.0 | |
|
|
| 2.8532 | 8.26 | 4800 | 3.0751 | 1.0 | |
|
|
| 2.8548 | 8.61 | 5000 | 3.0946 | 1.0 | |
|
|
| 2.8513 | 8.95 | 5200 | 3.0840 | 1.0 | |
|
|
| 2.845 | 9.29 | 5400 | 3.0896 | 1.0 | |
|
|
| 2.8592 | 9.64 | 5600 | 3.1055 | 1.0 | |
|
|
| 2.8453 | 9.98 | 5800 | 3.1124 | 1.0 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.19.2 |
|
|
- Pytorch 1.11.0+cu113 |
|
|
- Datasets 2.2.2 |
|
|
- Tokenizers 0.12.1 |
|
|
|
