metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
model-index:
- name: Whisper-small-Jibbali_lang_ex2
results: []
Whisper-small-Jibbali_lang_ex2
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0082
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 |
|---|---|---|---|
| 0.0317 | 1.0 | 225 | 0.0245 |
| 0.0188 | 2.0 | 450 | 0.0147 |
| 0.0065 | 3.0 | 675 | 0.0143 |
| 0.0163 | 4.0 | 900 | 0.0110 |
| 0.0038 | 5.0 | 1125 | 0.0083 |
| 0.0025 | 6.0 | 1350 | 0.0079 |
| 0.0027 | 7.0 | 1575 | 0.0079 |
| 0.0003 | 8.0 | 1800 | 0.0083 |
| 0.0026 | 9.0 | 2025 | 0.0084 |
| 0.0013 | 10.0 | 2250 | 0.0082 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2