Iamth0u/whisper-base-5_5

Whisper Small Hi - Sanchit Gandhi

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: 1.4291
• Wer: 17.4168

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
0.0996	1.7483	1000	0.8805	18.0539
0.0199	3.4965	2000	1.2566	17.4210
0.0039	5.2448	3000	1.3815	17.4086
0.0027	6.9930	4000	1.4291	17.4168

Framework versions

• Transformers 4.50.3
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0