CheeLi03/whisper-small-zh

Whisper Small Chinese - Chee Li

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

• Loss: 0.2650
• Wer: 21.6241

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
0.0088	4.3668	1000	0.2373	18.5336
0.0009	8.7336	2000	0.2523	17.6202
0.0005	13.1004	3000	0.2612	21.1278
0.0004	17.4672	4000	0.2650	21.6241

Framework versions

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