deepdml/whisper-medium-uk-cv17

Whisper Medium uk

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: 0.2943
• Wer: 10.9125

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
0.2039	0.9099	1000	0.2393	14.0916
0.0942	1.8198	2000	0.2207	11.8428
0.0463	2.7298	3000	0.2303	11.5953
0.0156	3.6397	4000	0.2701	11.0438
0.0041	4.5496	5000	0.2943	10.9125

Framework versions

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