joey234/whisper-small-vi

Whisper Small Vietnamese

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

• Loss: 0.9921
• Wer: 34.2172

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: 64
• eval_batch_size: 32
• 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0002	124.0	1000	0.7998	21.7706
0.0001	249.0	2000	0.8833	28.9690
0.0	374.0	3000	0.9382	30.8206
0.0	499.0	4000	0.9754	34.4363
0.0	624.0	5000	0.9921	34.2172

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0
• Datasets 2.7.1
• Tokenizers 0.13.2