jun-han/whisper-small-zh_chinese

Whisper-Keep-train

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

• Loss: 4.0346
• Cer: 736.0397

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
3.4342	0.8065	50	4.1335	275.1466
3.0912	1.6129	100	4.1066	265.1782
2.7991	2.4194	150	4.0602	318.1326
2.6758	3.2258	200	4.0346	736.0397

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1