Whisper Small Hindi - Prateep Mukherjee

This model is a fine-tuned version of openai/whisper-small on the Common Voice Scripted Speech 26.0 - Hindi dataset.

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_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: 3000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 5.8.1
• Pytorch 2.13.0+cu129
• Datasets 4.8.5
• Tokenizers 0.22.2