Downloads · 30 days
4
24% of all-time downloads
whisper_ee
ahmad1703/whisper_ee
whisper_ee is a machine learning model from ahmad1703. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model performs binary classification on audio using OpenAI's Whisper-small as a base model. It's designed to be used via the Hugging Face API for inference.
All-time downloads
17
Public
Repo size
967 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin967 MB · 100%
At a glance
- Model type
- whisper_classifier
- Access
- Public
- Created
- Apr 17, 2025
- Updated
- Apr 17, 2025
- SHA
- 4ce53b01
Model card
From the Hugging Face model README
Whisper Binary Audio Classifier
This model performs binary classification on audio using OpenAI's Whisper-small as a base model. It's designed to be used via the Hugging Face API for inference.
Model Details
- Base model: openai/whisper-small
- Task: Binary Audio Classification
- Output: Binary classification (0 or 1)
API Usage
from transformers import WhisperProcessor, pipeline
import librosa
# Load processor and pipeline
processor = WhisperProcessor.from_pretrained("ahmad1703/whis_ee")
classifier = pipeline("audio-classification", model="ahmad1703/whis_ee")
# Prepare your audio
audio_path = "path/to/your/audio.wav"
audio, sr = librosa.load(audio_path, sr=16000)
# Get prediction
prediction = classifier(audio)
print(f"Prediction: {prediction}")
Limitations
- This model works best with clean audio recordings
- Input audio should have a sampling rate of 16kHz
- [Add any other limitations here]
Contact
[Your contact information]
- Type
- whisper_classifier
- Created
- Apr 17, 2025
- Updated
- Apr 17, 2025