Downloads · 30 days
0
Genre_prediction
Kirandwip/Genre_prediction
Genre_prediction is a audio classification model from Kirandwip. Use it for the audio classification task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Music genre classifier trained on the Messy Mashup competition dataset.
Access
Public
Updated Apr 12, 2026
Repo size
43.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth43.4 MB · 100%
At a glance
- Task
- Audio Classification
- License
- mit
- Access
- Public
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026
- SHA
- 2eedd1dc
Model card
From the Hugging Face model README
Genre Classification — EfficientNet-B3
Music genre classifier trained on the Messy Mashup competition dataset.
Classes
blues, classical, country, disco, hiphop, jazz, metal, pop, reggae, rock
Architecture
EfficientNet-B3 fine-tuned on mel spectrograms (128 mel bins, 5s clips, 22050 Hz).
How to load
import torch
from torchvision import models
from huggingface_hub import hf_hub_download
model_path = hf_hub_download(repo_id="Kirandwip/Genre_prediction", filename="perfection_model_99.pth")
model = models.efficientnet_b3(weights=None)
model.classifier[1] = torch.nn.Linear(model.classifier[1].in_features, 10)
model.load_state_dict(torch.load(model_path, map_location="cpu"))
model.eval()
- Task
- Audio Classification
- License
- mit
- Languages
- en
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026