whisper-small-zh-hk

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: 0.2332
• Wer: 200.4809

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: 8
• 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
0.3422	0.5708	1000	0.3029	237.3286
0.1806	1.1416	2000	0.2574	181.2467
0.1626	1.7123	3000	0.2383	171.2199
0.0892	2.2831	4000	0.2332	200.4809

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3