whisper-small-lang-id
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3220
- Accuracy: 0.9555
- F1: 0.9549
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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.0498 | 0.25 | 2500 | 0.2722 | 0.9578 | 0.9576 |
| 0.0039 | 1.12 | 5000 | 0.6877 | 0.8952 | 0.8901 |
| 0.0 | 1.38 | 7500 | 0.2562 | 0.9532 | 0.9526 |
| 0.0 | 2.25 | 10000 | 0.3220 | 0.9555 | 0.9549 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2