whisper-tiny-300v2

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

• Loss: 1.4117
• Wer Ortho: 83.7838
• Wer: 86.4865

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: 16
• seed: 42
• 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
0.2322	20.0	60	1.3194	83.7838	83.7838
0.0267	40.0	120	1.3785	81.0811	81.0811
0.0002	60.0	180	1.3838	81.0811	81.0811
0.0001	80.0	240	1.4049	83.7838	83.7838
0.0	100.0	300	1.4117	83.7838	86.4865

Framework versions

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