vignesh-trustt/whisper-large-v3-indic-multilingual

Whisper Large V3 Indic

This model is a fine-tuned version of openai/whisper-large-v3 on the Indic Voices dataset. It achieves the following results on the evaluation set:

• Loss: 0.2960
• Wer: 0.5104

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 OptimizerNames.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
0.1739	1.4535	1000	0.2531	0.5681
0.0933	2.9070	2000	0.2297	0.5334
0.0262	4.3605	3000	0.2665	0.5182
0.0097	5.8140	4000	0.2960	0.5104

Framework versions

• Transformers 4.48.0
• Pytorch 2.9.0+cu126
• Datasets 4.4.1
• Tokenizers 0.21.4