| --- |
| license: apache-2.0 |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: f03 |
| 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. --> |
|
|
| # f03 |
|
|
| This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.4065 |
| - Wer: 1.7943 |
|
|
| ## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 1000 |
| - num_epochs: 7 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Wer | |
| |:-------------:|:-----:|:----:|:---------------:|:------:| |
| | 9.3101 | 1.28 | 500 | 3.1493 | 1.0 | |
| | 2.656 | 2.56 | 1000 | 1.8592 | 1.9932 | |
| | 0.9393 | 3.84 | 1500 | 0.4962 | 2.1675 | |
| | 0.2317 | 5.12 | 2000 | 0.4691 | 1.9002 | |
| | 0.1108 | 6.39 | 2500 | 0.4065 | 1.7943 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.17.0 |
| - Pytorch 1.13.1+cu116 |
| - Datasets 1.18.3 |
| - Tokenizers 0.13.2 |
| |
