datdo2717/whisper-small-ori-en

Whisper Small Ori 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: 0.6465
• Wer: 15.6151

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: 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1101	2.2222	1000	0.4305	16.7958
0.0254	4.4444	2000	0.5225	15.7553
0.0034	6.6667	3000	0.6075	15.5118
0.0011	8.8889	4000	0.6465	15.6151

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.0
• Datasets 3.1.0
• Tokenizers 0.20.0