arun100/whisper-small-zh-1

Whisper Small Chinese-Mandarin

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_16_0 zh-CN dataset. It achieves the following results on the evaluation set:

• Loss: 0.3738
• Wer: 77.8599

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: 5e-07
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7234	1.06	500	0.4390	82.2706
0.5601	3.0	1000	0.3994	80.4089
0.6714	4.06	1500	0.3857	79.6694
0.4956	6.0	2000	0.3784	78.1383
0.6296	7.06	2500	0.3751	78.4863
0.4632	9.0	3000	0.3738	77.8599

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.16.2.dev0
• Tokenizers 0.15.0