--- license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer datasets: - audiofolder metrics: - wer model-index: - name: whisper-small-ft_custom results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: audiofolder type: audiofolder config: default split: None args: default metrics: - name: Wer type: wer value: 2.3166023166023164 --- # whisper-small-ft_custom This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the audiofolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0000 - Wer: 2.3166 ## 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: 16 - eval_batch_size: 8 - 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: 4000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:----:|:---------------:|:-------:| | 0.0001 | 500.0 | 500 | 0.0001 | 37.0656 | | 0.0001 | 1000.0 | 1000 | 0.0001 | 37.0656 | | 0.0001 | 1500.0 | 1500 | 0.0001 | 2.3166 | | 0.0 | 2000.0 | 2000 | 0.0000 | 2.3166 | | 0.0 | 2500.0 | 2500 | 0.0000 | 2.3166 | | 0.0 | 3000.0 | 3000 | 0.0000 | 2.3166 | | 0.0 | 3500.0 | 3500 | 0.0000 | 2.3166 | | 0.0 | 4000.0 | 4000 | 0.0000 | 2.3166 | ### Framework versions - Transformers 4.37.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2