| --- |
| license: apache-2.0 |
| tags: |
| - generated_from_trainer |
| metrics: |
| - wer |
| model-index: |
| - name: assis |
| 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. --> |
|
|
| # assis |
|
|
| 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: 0.3864 |
| - Wer: 1 |
|
|
| ## 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: 1e-05 |
| - train_batch_size: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - gradient_accumulation_steps: 2 |
| - total_train_batch_size: 16 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 3000 |
| - training_steps: 5000 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Wer | |
| |:-------------:|:-----:|:----:|:---------------:|:---:| |
| | 3.006 | 15.62 | 1000 | 2.9606 | 1 | |
| | 2.8532 | 31.25 | 2000 | 2.8553 | 1 | |
| | 0.6421 | 46.88 | 3000 | 0.5418 | 1 | |
| | 0.3404 | 62.5 | 4000 | 0.4027 | 1 | |
| | 0.2801 | 78.12 | 5000 | 0.3864 | 1 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.27.4 |
| - Pytorch 1.13.1 |
| - Datasets 2.11.0 |
| - Tokenizers 0.13.2 |
|
|
