whisper-tiny-en

This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6966
• Wer Ortho: 0.2806
• Wer: 0.2828

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: 50
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0008	17.24	500	0.5855	0.2740	0.2758
0.0002	34.48	1000	0.6411	0.2780	0.2809
0.0001	51.72	1500	0.6713	0.2793	0.2815
0.0001	68.97	2000	0.6966	0.2806	0.2828

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3