whisper-small-yue-full-1
This model is a fine-tuned version of safecantonese/whisper-small-yue-full on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0362
- Cer: 6.1457
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0147 | 0.88 | 1000 | 0.0406 | 6.2936 |
| 0.0083 | 1.76 | 2000 | 0.0362 | 6.1457 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1