Whisper Small SIT 08 07 26 0758

--- library_name: transformers license: mit base_model: Pengwin30/whisper-small-fine-tuned tags: - generated_from_trainer metrics: - wer model-index: - name: whisper-small-SIT_08_07_26_0758 results: [] --- # whisper-small-SIT_08_07_26_0758 This model is a fine-tuned version of [Pengwin30/whisper-small-fine-tuned](https://huggingface.co/Pengwin30/whisper-small-fine-tuned) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0296 - Wer: 1.3254 ## 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: 8 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - 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 | |:-------------:|:-----:|:----:|:---------------:|:------:| | 0.4535 | 1.0 | 361 | 0.0211 | 1.5905 | | 0.0296 | 2.0 | 722 | 0.0294 | 1.3917 | | 0.0066 | 3.0 | 1083 | 0.0296 | 1.3254 | ### Framework versions - Transformers 5.12.1 - Pytorch 2.11.0+cu128 - Datasets 2.19.0 - Tokenizers 0.22.2