deepdml/whisper-medium-eu-cv17

Whisper Medium eu

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: 0.1067
• Wer: 6.2269

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
0.1766	0.3596	1000	0.1877	12.7130
0.1372	0.7192	2000	0.1370	8.7444
0.0634	1.0787	3000	0.1210	7.2108
0.0558	1.4383	4000	0.1119	6.5411
0.0631	1.7979	5000	0.1067	6.2269

Framework versions

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