whisper-sm-urdu-finetuned

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1777
• Wer: 36.0220

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: 16
• 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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4017	0.18	1000	0.2591	65.3388
0.3963	0.36	2000	0.2135	43.6355
0.3162	0.54	3000	0.1880	35.8573
0.3479	0.72	4000	0.1777	36.0220

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1
• Datasets 2.14.5
• Tokenizers 0.13.3