metadata
language:
- zh
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper tiny ZH
results: []
Whisper tiny ZH
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4274
- Wer: 72.8392
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: 16
- eval_batch_size: 8
- seed: 42
- 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 |
|---|---|---|---|---|
| 0.3122 | 1.42 | 1000 | 0.4312 | 80.1869 |
| 0.2145 | 2.84 | 2000 | 0.4149 | 70.8855 |
| 0.1147 | 4.26 | 3000 | 0.4247 | 76.5980 |
| 0.094 | 5.67 | 4000 | 0.4274 | 72.8392 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.2.0a0+6a974be
- Datasets 2.16.1
- Tokenizers 0.15.0