| # WhisperClassifier for Binary Audio Classification | |
| This is a binary classification model built on top of OpenAI's Whisper-small model. It takes audio features as input and predicts a binary class. | |
| ## Model Details | |
| - Base model: openai/whisper-small | |
| - Task: Binary Audio Classification | |
| - Training data: [Your training data details] | |
| - Evaluation results: [Your evaluation metrics] | |
| ## Usage | |
| ```python | |
| from transformers import WhisperProcessor | |
| import torch | |
| from predict import WhisperClassifier, predict, load_model | |
| # Load processor and model | |
| processor = WhisperProcessor.from_pretrained("ahmad1703/whis_ee") | |
| model, device = load_model("model.pth") | |
| # Example prediction | |
| audio_path = "path/to/your/audio_file.wav" | |
| result = predict(model, audio_path, processor, device) | |
| print(f"Prediction: {result}") # 0 or 1 | |
| ``` | |
| ## Citation | |
| If you use this model in your research, please cite: | |
| ``` | |
| @misc{whisperclassifier2025, | |
| author = {[Your Name]}, | |
| title = {WhisperClassifier for Binary Audio Classification}, | |
| year = {2025}, | |
| publisher = {HuggingFace}, | |
| howpublished = {\url{https://huggingface.co/ahmad1703/whis_ee}} | |
| } | |
| ``` | |