Amit65/whisper-small-hi-V2.1

Whisper Small Mr - Amit Rai

This model is a fine-tuned version of openai/whisper-small on the Common Voice mr 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4063
• Wer: 47.5340

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: 8
• 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
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0469	3.5587	1000	0.3397	48.4430
0.0027	7.1174	2000	0.4063	47.5340

Framework versions

• Transformers 4.51.3
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0