Downloads · 30 days
4
13% of all-time downloads
ast-finetuned-gtzan-audio-course
herurg/ast-finetuned-gtzan-audio-course
ast-finetuned-gtzan-audio-course is a audio classification model from herurg. Use it for the audio classification task on the model card, and read the license before you ship it in a product.
Fine-tuned from MIT/ast-finetuned-audioset-10-10-0.4593 on marsyas/gtzan for the Hugging Face Audio Course Unit 4 hands-on assignment.
All-time downloads
30
Public
Parameters
86.2M
345 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors345 MB · 100%
At a glance
- Task
- Audio Classification
- Model type
- audio-spectrogram-transformer
- Access
- Public
- Created
- Aug 22, 2026
- Updated
- Aug 22, 2026
- SHA
- 3ce21de4
Base models
Datasets
Model card
From the Hugging Face model README
AST fine-tuned on GTZAN
Fine-tuned from
MIT/ast-finetuned-audioset-10-10-0.4593
on marsyas/gtzan for the Hugging Face Audio Course
Unit 4 hands-on assignment.
Evaluation
Accuracy: 0.880000
Audio Course requirement: Accuracy >= 0.87.
Dataset
- Dataset:
marsyas/gtzan - Training examples: 899
- Evaluation examples: 100
- Genres: blues, classical, country, disco, hiphop, jazz, metal, pop, reggae, rock
- Task
- Audio Classification
- Type
- audio-spectrogram-transformer
- Languages
- en
- Created
- Aug 22, 2026
- Updated
- Aug 22, 2026