chandc/whisper-small-Cantonese

Whisper Small Cantonese - Daniel Chan

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2611
• Wer: 55.8860

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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2222	1.14	1000	0.2847	63.1879
0.1146	2.28	2000	0.2592	58.2725
0.0382	3.42	3000	0.2575	55.9216
0.024	4.57	4000	0.2611	55.8860

Framework versions

• Transformers 4.38.1
• Pytorch 2.2.0
• Datasets 2.17.0
• Tokenizers 0.15.2