whisper-small-300v2

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

• Loss: 0.9642
• Wer Ortho: 67.5676
• Wer: 67.5676

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
• gradient_accumulation_steps: 2
• 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
0.8789	20.0	60	1.2473	70.2703	70.2703
0.0015	40.0	120	0.9230	72.9730	72.9730
0.0	60.0	180	0.9398	67.5676	67.5676
0.0	80.0	240	0.9529	67.5676	67.5676
0.0	100.0	300	0.9642	67.5676	67.5676

Framework versions

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