metadata
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
- generated_from_trainer
model-index:
- name: Whisper-small-Arabic-phoneme
results: []
Whisper-small-Arabic-phoneme
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2263
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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0558 | 1.0 | 546 | 0.2097 |
| 0.0475 | 2.0 | 1092 | 0.2145 |
| 0.0471 | 3.0 | 1638 | 0.1868 |
| 0.022 | 4.0 | 2184 | 0.1879 |
| 0.0185 | 5.0 | 2730 | 0.1933 |
| 0.0118 | 6.0 | 3276 | 0.1861 |
| 0.0148 | 7.0 | 3822 | 0.1903 |
| 0.0044 | 8.0 | 4368 | 0.2087 |
| 0.0045 | 9.0 | 4914 | 0.2150 |
| 0.0027 | 10.0 | 5460 | 0.2263 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1