whisper-vi

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: 0.7590
• Wer: 27.4043

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: 24
• eval_batch_size: 12
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.006	8.6207	1000	0.6403	30.3103
0.0004	17.2414	2000	0.7165	27.3056
0.0002	25.8621	3000	0.7476	27.4372
0.0002	34.4828	4000	0.7590	27.4043

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.1+cu118
• Datasets 3.1.0
• Tokenizers 0.20.3