IoanaLiviaPopescu/real-data-synth-data-400-1-Wavnet-B-whisper-small-v0
This model is a fine-tuned version of openai/whisper-small on the IoanaLiviaPopescu/RealVoiceSynthVoice-400-1-Wavnet-B dataset. It achieves the following results on the evaluation set:
- Loss: 0.4064
- Wer: 18.1634
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: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0 | 0 | 0.6024 | 27.8812 |
| 0.3905 | 1.0 | 26 | 0.4462 | 19.8230 |
| 0.1805 | 2.0 | 52 | 0.3922 | 18.6428 |
| 0.1043 | 3.0 | 78 | 0.3919 | 18.2187 |
| 0.0697 | 4.0 | 104 | 0.4040 | 18.5691 |
| 0.0534 | 5.0 | 130 | 0.4064 | 18.1634 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1