| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: openai/whisper-tiny.en |
| tags: |
| - generated_from_trainer |
| metrics: |
| - wer |
| model-index: |
| - name: fs-w-xavier-tiny-en |
| 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. --> |
|
|
| # fs-w-xavier-tiny-en |
|
|
| This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.4493 |
| - Wer: 107.1700 |
| - Cer: 86.3964 |
|
|
| ## 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: 16 |
| - 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: 500 |
| - training_steps: 5000 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
| |:-------------:|:-------:|:----:|:---------------:|:--------:|:-------:| |
| | 4.3581 | 4.5872 | 500 | 4.4334 | 98.1956 | 76.2625 | |
| | 1.7975 | 9.1743 | 1000 | 2.0190 | 106.9801 | 83.2016 | |
| | 0.7013 | 13.7615 | 1500 | 1.0136 | 109.8765 | 87.5816 | |
| | 0.4308 | 18.3486 | 2000 | 0.6682 | 107.5024 | 85.6235 | |
| | 0.3656 | 22.9358 | 2500 | 0.5726 | 107.5973 | 84.8677 | |
| | 0.3092 | 27.5229 | 3000 | 0.5117 | 106.7901 | 85.4775 | |
| | 0.2605 | 32.1101 | 3500 | 0.4788 | 104.1785 | 84.2580 | |
| | 0.236 | 36.6972 | 4000 | 0.4664 | 105.1757 | 84.8162 | |
| | 0.2298 | 41.2844 | 4500 | 0.4561 | 106.2678 | 85.5891 | |
| | 0.2007 | 45.8716 | 5000 | 0.4493 | 107.1700 | 86.3964 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.45.1 |
| - Pytorch 2.4.1+cu121 |
| - Datasets 3.0.1 |
| - Tokenizers 0.20.0 |
| |
