| language: multilingual | |
| license: apache-2.0 | |
| tags: | |
| - audio-classification | |
| - whisper | |
| - speech | |
| - music | |
| datasets: | |
| - AIGenLab/speech-music-merge | |
| base_model: openai/whisper-small | |
| pipeline_tag: audio-classification | |
| # Whisper Small - Speech/Music Classifier | |
| Whisper Small fine-tuned for speech vs music classification. | |
| ## Usage | |
| ```python | |
| from transformers import pipeline | |
| classifier = pipeline("audio-classification", model="AIGenLab/whisper-small-speech-music-classifier") | |
| result = classifier("audio.wav") | |
| print(result) | |
| ``` | |
| ## Details | |
| - **Base:** openai/whisper-small | |
| - **Dataset:** AIGenLab/speech-music-merge | |
| - **Classes:** speech, music | |
| - **Sample Rate:** 16kHz | |