whisper_medium_zh

This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9767
• Wer: 96.0
• Cer: 12.6058

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 40
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
No log	0.48	10	2.7665	98.0	13.0762
No log	0.95	20	2.6914	98.0	13.0762
2.4583	1.43	30	2.2921	98.0	12.8881
2.4583	1.9	40	1.9767	96.0	12.6058

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.12.0
• Tokenizers 0.12.1