whisper-small-vivos

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2580
• Wer: 17.6379
• Cer: 7.0276

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: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.1276	1.37	1000	0.2137	20.6164	8.6876
0.0696	2.74	2000	0.2173	19.0883	7.5097
0.0215	4.12	3000	0.2420	17.9876	7.0794
0.0199	5.49	4000	0.2580	17.6379	7.0276

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.0
• Datasets 2.14.4
• Tokenizers 0.13.3