| | --- |
| | license: apache-2.0 |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: loso_M12 |
| | 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. --> |
| |
|
| | # loso_M12 |
| | |
| | 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: 0.0778 |
| | - Wer: 1.4221 |
| | |
| | ## 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 | |
| | |:-------------:|:-----:|:----:|:---------------:|:------:| |
| | | 8.3422 | 0.95 | 500 | 3.5867 | 1.0 | |
| | | 2.553 | 1.89 | 1000 | 1.4240 | 2.6174 | |
| | | 0.8451 | 2.84 | 1500 | 0.2177 | 1.6943 | |
| | | 0.2944 | 3.79 | 2000 | 0.1941 | 1.7673 | |
| | | 0.1312 | 4.73 | 2500 | 0.1034 | 1.3669 | |
| | | 0.079 | 5.68 | 3000 | 0.0695 | 1.2722 | |
| | | 0.0457 | 6.63 | 3500 | 0.0778 | 1.4221 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.17.0 |
| | - Pytorch 1.13.1+cu116 |
| | - Datasets 1.18.3 |
| | - Tokenizers 0.13.2 |
| |
|
