--- license: apache-2.0 base_model: openai/whisper-medium.en tags: - generated_from_trainer metrics: - wer model-index: - name: medium results: [] --- [Visualize in Weights & Biases](https://wandb.ai/imannalia/augment_thirty_whisper_ft_medium/runs/lx7hkern) # medium This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4547 - Wer: 11.8776 - Cer: 7.0531 - Wer Normalized: 11.8782 ## 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: 32 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 1500 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Wer Normalized | |:-------------:|:------:|:----:|:---------------:|:-------:|:------:|:--------------:| | 0.7386 | 1.7544 | 500 | 0.3919 | 9.6967 | 5.7829 | 9.6942 | | 0.3228 | 3.5088 | 1000 | 0.4447 | 10.0253 | 6.0106 | 10.0254 | | 0.1196 | 5.2632 | 1500 | 0.5873 | 10.2440 | 6.1735 | 10.2441 | ### Framework versions - Transformers 4.41.0 - Pytorch 2.1.1+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1