whisper-small-chinese-tw

This model is a fine-tuned version of openai/whisper-small on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2167
• Wer: 39.7324

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	Wer
0.0957	1.4184	1000	0.1986	40.8792
0.0315	2.8369	2000	0.2038	40.4544
0.0036	4.2553	3000	0.2102	40.1571
0.0018	5.6738	4000	0.2167	39.7324

Framework versions

• Transformers 4.46.2
• Pytorch 2.4.0+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3