Whisper Small Gurmukhi LoRA

--- library_name: peft license: apache-2.0 base_model: openai/whisper-small tags: - base_model:adapter:openai/whisper-small - lora - transformers - asr - transcription - panjabi model-index: - name: whisper-small-gurmukhi-lora results: [] datasets: - abhi8799/Punjabi-STT-Small-8H language: - pa --- # whisper-small-gurmukhi-lora This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.8086 ## 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: 0.0001 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - 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 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:--------:|:----:|:---------------:| | 1.0380 | 66.7273 | 200 | 0.4913 | | 0.2082 | 133.3636 | 400 | 0.6787 | | 0.0179 | 200.0 | 600 | 0.7486 | | 0.0077 | 266.7273 | 800 | 0.7866 | | 0.0056 | 333.3636 | 1000 | 0.8086 | ### Framework versions - PEFT 0.19.1 - Transformers 5.10.2 - Pytorch 2.11.0+cu128 - Datasets 5.0.0 - Tokenizers 0.22.2