SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.11276 · 2023

Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
crypto-code/mu-llama canonical 3 of 4
FunctionStatusWhere it lives
apply_rotary_emb Ran crypto-code/mu-llama/MU-LLaMA/llama/llama.py
pointer only (licence: GPL-3.0) · get_code("b47d48e431b34acd")
precompute_freqs_cis Ran crypto-code/mu-llama/MU-LLaMA/llama/llama.py
pointer only (licence: GPL-3.0) · get_code("14a84c2cbfebc413")
reshape_for_broadcast Ran crypto-code/mu-llama/MU-LLaMA/llama/llama.py
pointer only (licence: GPL-3.0) · get_code("70bf6ebaafd266c4")
split_audio Not yet run crypto-code/mu-llama/ModelEvaluations/generate_llama-adapter.py
pointer only (licence: GPL-3.0) · get_code("fc374848fd574449")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Text-to-music generation (T2M-Gen) faces a major obstacle due to the scarcity of large-scale publicly available music datasets with natural language captions. To address this, we propose the Music Understanding LLaMA (MU-LLaMA), capable of answering music-related questions and generating captions for music files. Our model utilizes audio representations from a pretrained MERT model to extract music features. However, obtaining a suitable dataset for training the MU-LLaMA model remains challenging, as existing publicly accessible audio question answering datasets lack the necessary depth for open-ended music question answering. To fill this gap, we present a methodology for generating question-answer pairs from existing audio captioning datasets and introduce the MusicQA Dataset designed for answering open-ended music-related questions. The experiments demonstrate that the proposed MU-LLaMA model, trained on our designed MusicQA dataset, achieves outstanding performance in both music question answering and music caption generation across various metrics, outperforming current state-of-the-art (SOTA) models in both fields and offering a promising advancement in the T2M-Gen research field.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2308.11276")
get_code_for_paper("2308.11276")
have("2308.11276")

Connect an agent — have() is free.