arun100/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: 0.8001
• Wer: 27.7034

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	0.8001	27.7034
0.0001	249.0	2000	0.8835	33.8561
0.0	374.0	3000	0.9383	36.0386
0.0	499.0	4000	0.9755	36.2689
0.0	624.0	5000	0.9923	38.3746

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2