whisper-medium-en-cv-6.0

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

• Loss: 1.1135
• Wer: 34.7214

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: 48
• eval_batch_size: 4
• 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: 150
• training_steps: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0	0	2.4185	46.5401
0.7543	0.2	300	0.9822	37.0178
0.3116	1.2	600	0.9713	35.2725
0.124	2.2	900	1.0252	34.4152
0.0523	3.2	1200	1.0789	34.4764
0.0269	4.2	1500	1.1135	34.7214

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.1
• Tokenizers 0.21.1