whisper-large-v3-turbo-Punjabi-Version1

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3767
• Wer: 56.5078

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• training_steps: 20000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2097	15.625	2000	0.3250	59.6746
0.138	31.25	4000	0.2924	56.5078
0.0979	46.875	6000	0.2903	54.3870
0.0732	62.5	8000	0.3096	55.8977
0.0528	78.125	10000	0.3214	53.8059
0.0421	93.75	12000	0.3443	56.4207
0.0299	109.375	14000	0.3594	55.2876
0.0267	125.0	16000	0.3767	56.5078

Framework versions

• PEFT 0.14.0
• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0