deepdml/whisper-medium-pt-cv17

Whisper Medium pt

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2757
• Wer: 6.9248

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1211	1.0173	1000	0.2010	7.8295
0.0393	2.0346	2000	0.2084	7.3020
0.0167	3.0519	3000	0.2243	7.0191
0.0049	4.0692	4000	0.2530	6.9807
0.0018	5.0865	5000	0.2757	6.9248

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1