--- license: apache-2.0 base_model: emonidi/whisper-order-finetuned-bg tags: - generated_from_trainer metrics: - wer model-index: - name: whisper-order-finetuned-bg results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper-order-finetuned-bg This model is a fine-tuned version of [emonidi/whisper-order-finetuned-bg](https://huggingface.co/emonidi/whisper-order-finetuned-bg) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0001 - Wer: 0.0 ## 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: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 32 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 30 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:---:| | 0.0011 | 4.0 | 5 | 0.0016 | 0.0 | | 0.0001 | 7.38 | 10 | 0.0003 | 0.0 | | 0.0001 | 11.0 | 15 | 0.0002 | 0.0 | | 0.0 | 14.77 | 20 | 0.0001 | 0.0 | | 0.0 | 18.0 | 25 | 0.0001 | 0.0 | | 0.0 | 22.0 | 30 | 0.0001 | 0.0 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu121 - Datasets 2.15.0 - Tokenizers 0.15.0