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
- Downloads last month
- 15
Model tree for herurg/ast-finetuned-gtzan-audio-course
Base model
MIT/ast-finetuned-audioset-10-10-0.4593Dataset used to train herurg/ast-finetuned-gtzan-audio-course
Evaluation results
- Accuracy on GTZANtest set self-reported0.880