Whisper Small P0-KM V2
This model is a fine-tuned version of openai/whisper-small on the Recorded Voice Data dataset. It achieves the following results on the evaluation set:
- Loss: 0.8060
- Wer Ortho: 88.2353
- Wer: 52.7273
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: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0020 | 17.8571 | 500 | 0.7053 | 90.1961 | 58.9091 |
| 0.0000 | 35.7143 | 1000 | 0.8060 | 88.2353 | 52.7273 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2