Whisper Base Bisyllabic Jyutping
This model is a fine-tuned version of openai/whisper-base on the AlienKevin/cantone dataset. It achieves the following results on the evaluation set:
- Loss: 0.3613
- Wer: 41.25
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- training_steps: 2400
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1093 | 0.08 | 400 | 0.3231 | 51.0417 |
| 0.0389 | 0.15 | 800 | 0.2922 | 40.4861 |
| 0.0237 | 0.23 | 1200 | 0.3020 | 37.7778 |
| 0.0131 | 0.3 | 1600 | 0.3561 | 42.7083 |
| 0.01 | 0.38 | 2000 | 0.3817 | 44.6528 |
| 0.0095 | 0.46 | 2400 | 0.3613 | 41.25 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0
- Datasets 2.14.5
- Tokenizers 0.15.1
- Downloads last month
- 0