CheeLi03/whisper-base-zh

Whisper Base Chinese - Chee Li

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

• Loss: 0.4109
• Wer: 21.0151

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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0705	4.3668	1000	0.3557	23.0095
0.0066	8.7336	2000	0.3853	21.0578
0.0026	13.1004	3000	0.4046	20.9695
0.002	17.4672	4000	0.4109	21.0151

Framework versions

• Transformers 4.43.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1