anuragshas/whisper-small-ur

Whisper Small Urdu

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

• Loss: 0.7803
• Wer: 32.6814

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: 64
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2634	3.85	200	0.5562	43.3518
0.0592	7.69	400	0.6271	40.8807
0.0121	11.54	600	0.7298	35.4506
0.0048	15.38	800	0.7803	32.6814
0.0039	19.23	1000	0.7940	33.3243

Framework versions

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