momo103197/whisper-small-zh-TW-16

Whisper Small zh-TW - Fine-tune-16

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2186
• Cer: 9.2827

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: Use 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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0462	2.2523	1000	0.1969	9.6684
0.0075	4.5045	2000	0.2071	9.5586
0.0015	6.7568	3000	0.2146	9.1627
0.0007	9.0090	4000	0.2186	9.2827

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0