geninhu/whisper-medium-az

Whisper Medium Azerbaijani

This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 az dataset. It achieves the following results on the evaluation set:

• Loss: 0.7751
• Wer: 47.3373

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: 32
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0	499.0	1000	0.7751	47.3373
0.0	999.0	2000	0.8982	47.3373
0.0	1499.0	3000	0.9612	47.9290
0.0	1999.0	4000	1.0112	47.9290
0.0	2499.0	5000	1.0212	47.9290

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2