vishal2304/whisper-small-ta

Whisper Small En - Vishal Sankar Ram

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4155
• Wer: 67.4277

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
• lr_scheduler_warmup_steps: 5
• training_steps: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.08	10	0.5279	73.3638
No log	0.16	20	0.4622	70.7763
0.45	0.24	30	0.4298	69.2542
0.45	0.32	40	0.4193	67.1233
0.334	0.4	50	0.4155	67.4277

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0