whisper-medium.en

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

• Loss: 1.7011
• Wer: 0.0

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.8998	1.25	5	2.2823	0.0
2.608	2.5	10	2.0390	0.0
2.2464	3.75	15	1.9019	0.0
1.8177	5.0	20	1.7011	0.0

Framework versions

• Transformers 4.50.1
• Pytorch 2.6.0
• Datasets 3.6.0
• Tokenizers 0.21.1