| --- |
| license: apache-2.0 |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: EnglishModel |
| 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. --> |
|
|
| # EnglishModel |
|
|
| 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: 3.1449 |
| - 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: 0.03 |
| - train_batch_size: 1 |
| - eval_batch_size: 8 |
| - seed: 45 |
| - gradient_accumulation_steps: 8 |
| - total_train_batch_size: 8 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 300 |
| - num_epochs: 3 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Wer | |
| |:------------------:|:-----:|:----:|:---------------:|:---:| |
| | 1905.1503 | 0.98 | 600 | 3.1449 | 1.0 | |
| | 4586886945979761.0 | 1.96 | 1200 | 3.1449 | 1.0 | |
| | 4847837820171059.0 | 2.94 | 1800 | 3.1449 | 1.0 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.11.3 |
| - Pytorch 1.10.0+cu113 |
| - Datasets 2.9.0 |
| - Tokenizers 0.10.3 |
|
|
