|
--- |
|
library_name: transformers |
|
license: cc-by-nc-4.0 |
|
base_model: facebook/mms-1b-all |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: wav2vec2-large-mms-1b-dzo-colab |
|
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-large-mms-1b-dzo-colab |
|
|
|
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4692 |
|
- Wer: 0.4020 |
|
|
|
## 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: 0.004 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Use OptimizerNames.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: 500 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 1.8364 | 1.0 | 13 | 1.7411 | 0.8907 | |
|
| 1.8276 | 2.0 | 26 | 1.5980 | 0.8391 | |
|
| 1.6815 | 3.0 | 39 | 1.4269 | 0.7822 | |
|
| 1.4402 | 4.0 | 52 | 1.2306 | 0.7050 | |
|
| 1.3527 | 5.0 | 65 | 1.0515 | 0.6605 | |
|
| 1.1983 | 6.0 | 78 | 0.8829 | 0.5821 | |
|
| 0.99 | 7.0 | 91 | 0.7602 | 0.5550 | |
|
| 0.9221 | 8.0 | 104 | 0.6441 | 0.4770 | |
|
| 0.8035 | 9.0 | 117 | 0.5535 | 0.4503 | |
|
| 0.6713 | 10.0 | 130 | 0.4692 | 0.4020 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.49.0.dev0 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
