We propose the MusicQA dataset to train Music-enabled question-answering models and is used for training and evaluating our MU-LLaMA model. This dataset is generated using the MusicCaps and MagnaTagATune datasets. We utilize the descriptions/tags from existing datasets to prompt the MPT-7B Chat model to generate question-answer pairs through inference, reasoning, and paraphrasing. The dataset contains 12,542 music files for training making up 76.15 hours of music with 112,878 question-answer pairs.
Variants: MusicQA
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Music Question Answering | MU-LLaMA | Music Understanding LLaMA: Advancing Text-to-Music … | 2023-08-22 |
| Music Question Answering | LTU | Listen, Think, and Understand | 2023-05-18 |
| Music Question Answering | LLaMA Adapter | LLaMA-Adapter: Efficient Fine-tuning of Language … | 2023-03-28 |
Recent papers with results on this dataset: