<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Whisper large-v2 nan-tw
This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 nan-tw dataset. It achieves the following results on the evaluation set:
- Loss: 0.7525
- Wer: 42.5930
- Cer: 23.2970
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: 2
- 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.4781 | 1.04 | 1000 | 0.7256 | 52.4690 | 28.7583 |
| 0.1881 | 2.08 | 2000 | 0.7346 | 50.2067 | 26.6389 |
| 0.0429 | 3.13 | 3000 | 0.7094 | 45.3557 | 24.7811 |
| 0.0112 | 5.01 | 4000 | 0.7416 | 44.4203 | 24.6850 |
| 0.0011 | 6.05 | 5000 | 0.7525 | 42.5930 | 23.2970 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.2
