simonl0909/whisper-large-v2-cantonese

Whisper Large V2 Cantonese

This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 yue dataset. It achieves the following results on the evaluation set:

• Loss: 0.2807
• Cer: 6.7274

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: 8
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0032	13.01	1000	0.2318	6.8569
0.002	26.01	2000	0.2404	7.1524
0.0001	39.02	3000	0.2807	6.7274
0.0001	53.01	4000	0.2912	6.7517
0.0	66.01	5000	0.2957	6.7638

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2