Whisper Small Cantanese
This model is a fine-tuned version of poppysmickarlili/whisper-small-cantonese_07-05-2024-2200 on the poppysmickarlili/common_voice_yue dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Wer: 0.0171
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: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0039 | 2.7816 | 1000 | 0.0040 | 1.3699 |
| 0.0006 | 5.5633 | 2000 | 0.0001 | 0.0514 |
| 0.0001 | 8.3449 | 3000 | 0.0001 | 0.0171 |
| 0.0 | 11.1377 | 4000 | 0.0000 | 0.0171 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.0
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 100
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for poppysmickarlili/whisper-small-cantonese
Base model
openai/whisper-smallDataset used to train poppysmickarlili/whisper-small-cantonese
Evaluation results
- Wer on poppysmickarlili/common_voice_yueself-reported0.017