whisper-medium-300v3

This model was trained from scratch on the audiofolder dataset.

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 30
• training_steps: 300

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0296	20.0	60	0.5458	59.4595	56.7568
0.0001	40.0	120	0.5378	43.2432	43.2432
0.0000	60.0	180	0.5364	43.2432	43.2432
0.0000	80.0	240	0.5390	43.2432	43.2432
0.0000	100.0	240	0.5389	43.2432	43.2432

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1