Whisper Small Jyutping without Tones (Trained on almost all open source Cantonese datasets)
This model is a fine-tuned version of openai/whisper-small on the Common Voice 14.0 Yue & zh-HK + MDCC dataset. It achieves the following results on the evaluation set:
- Loss: 0.0560
- Wer: 5.5162
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0655 | 0.07 | 1000 | 0.0948 | 8.6022 |
| 0.0577 | 0.13 | 2000 | 0.0747 | 6.9833 |
| 0.0496 | 0.2 | 3000 | 0.0627 | 6.8633 |
| 0.0558 | 0.27 | 4000 | 0.0560 | 5.5162 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3