perchaos/whisper-small-hi

Whisper Small Hindi - Fine-tuned

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: 0.5177
• Wer: 33.1880

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use adamw_torch_fused 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
0.0392	4.8802	1000	0.3348	34.2504
0.0026	9.7579	2000	0.4595	33.9499
0.0002	14.6357	3000	0.5030	33.1034
0.0002	19.5134	4000	0.5177	33.1880

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.0