| --- |
| license: apache-2.0 |
| base_model: openai/whisper-tiny |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: Whisper-tiny-Arabic-phoneme |
| 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. --> |
|
|
| # Whisper-tiny-Arabic-phoneme |
|
|
| This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.2115 |
|
|
| ## 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: 0.001 |
| - train_batch_size: 6 |
| - eval_batch_size: 6 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 50 |
| - num_epochs: 10 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 0.0703 | 1.0 | 546 | 0.2243 | |
| | 0.0452 | 2.0 | 1092 | 0.2117 | |
| | 0.0273 | 3.0 | 1638 | 0.1945 | |
| | 0.0239 | 4.0 | 2184 | 0.2105 | |
| | 0.0181 | 5.0 | 2730 | 0.1959 | |
| | 0.0124 | 6.0 | 3276 | 0.2083 | |
| | 0.0132 | 7.0 | 3822 | 0.2026 | |
| | 0.0066 | 8.0 | 4368 | 0.2110 | |
| | 0.0055 | 9.0 | 4914 | 0.2118 | |
| | 0.0029 | 10.0 | 5460 | 0.2115 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.35.2 |
| - Pytorch 2.1.0+cu118 |
| - Datasets 2.15.0 |
| - Tokenizers 0.15.0 |
| |
