Whisper Small chinese - yi ching
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2855
- Cer: 159.9017
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: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 | Cer |
|---|---|---|---|---|
| 0.045 | 2.84 | 1000 | 0.1841 | 118.0540 |
| 0.0037 | 5.67 | 2000 | 0.2238 | 113.5088 |
| 0.0002 | 8.51 | 3000 | 0.2538 | 105.2587 |
| 0.0 | 11.35 | 4000 | 0.2855 | 159.9017 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.12.1
- Datasets 2.14.5
- Tokenizers 0.14.1