Whisper Small zh - TEST
This model is a fine-tuned version of openai/whisper-small on the sample41 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0014
- Cer: 1.2671
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: 2
- eval_batch_size: 1
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 150
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0644 | 2.3810 | 50 | 0.0596 | 5.0682 |
| 0.0198 | 4.7619 | 100 | 0.0102 | 1.4620 |
| 0.0012 | 7.1429 | 150 | 0.0014 | 1.2671 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 190
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 TsaiYing/whisper-small-zh-test
Base model
openai/whisper-small