deepdml/whisper-medium-ar-cv17

Whisper Medium ar

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: 0.3309
• Wer: 52.5315

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
0.2054	0.8237	1000	0.2990	54.4903
0.1135	1.6474	2000	0.2926	63.7189
0.0618	2.4712	3000	0.3019	59.1518
0.0255	3.2949	4000	0.3154	53.1552
0.0141	4.1186	5000	0.3309	52.5315

Framework versions

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