whisper-large-v3-turbo-gurmukhi-lora

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

• Loss: 1.6186

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 100
• training_steps: 1000
• mixed_precision_training: Native AMP
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss
18.5560	1.25	50	2.2197
14.4289	2.5	100	1.7854
13.4670	3.75	150	1.6946
12.9902	5.0	200	1.6491
12.6007	6.25	250	1.6347
12.4687	7.5	300	1.6227
12.3255	8.75	350	1.6154
12.2176	10.0	400	1.6133
12.0832	11.25	450	1.6163
12.0028	12.5	500	1.6153
11.9251	13.75	550	1.6186

Framework versions

• PEFT 0.18.1
• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.5
• Tokenizers 0.22.2