Whisper Algerian Darja Small

--- library_name: peft license: apache-2.0 base_model: openai/whisper-small tags: - base_model:adapter:openai/whisper-small - lora - transformers metrics: - wer model-index: - name: whisper-algerian-darja-small results: [] --- # whisper-algerian-darja-small 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: 0.8546 - Wer: 68.2838 ## 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_TORCH_FUSED 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 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:----:|:---------------:|:-------:| | 5.4457 | 0.1558 | 100 | 1.2213 | 86.7625 | | 4.7419 | 0.3116 | 200 | 1.0291 | 72.0965 | | 4.1145 | 0.4675 | 300 | 0.8669 | 68.1661 | | 3.9718 | 0.6233 | 400 | 0.8257 | 64.4042 | | 3.6630 | 0.7849 | 500 | 0.8944 | 68.9757 | | 3.6994 | 0.9419 | 600 | 0.8722 | 69.1444 | | 3.5275 | 1.0989 | 700 | 0.8546 | 68.2838 | ### Framework versions - PEFT 0.19.1 - Transformers 5.13.0 - Pytorch 2.10.0+cu128 - Datasets 5.0.0 - Tokenizers 0.22.2