hanson92828/whisper-small-chinese-2

Whisper Small zh-TW - hanson92828

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2087
• Wer: 203.2213

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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0974	1.3263	1000	0.1997	167.3042
0.0218	2.6525	2000	0.1987	228.9309
0.0094	3.9788	3000	0.2022	221.2603
0.0025	5.3050	4000	0.2087	203.2213

Framework versions

• Transformers 4.46.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 2.19.2
• Tokenizers 0.20.1