Papers › Simple and Controllable Music Generation

Simple and Controllable Music Generation

8 Jun 2023NeurIPS 2023 11arXiv:2306.05284archive 2025-07-28

Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, Alexandre Défossez

We tackle the task of conditional music generation. We introduce MusicGen, a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens. Unlike prior work, MusicGen is comprised of a single-stage transformer LM together with efficient token interleaving patterns, which eliminates the need for cascading several models, e.g., hierarchically or upsampling. Following this approach, we demonstrate how MusicGen can generate high-quality samples, both mono and stereo, while being conditioned on textual description or melodic features, allowing better controls over the generated output. We conduct extensive empirical evaluation, considering both automatic and human studies, showing the proposed approach is superior to the evaluated baselines on a standard text-to-music benchmark. Through ablation studies, we shed light over the importance of each of the components comprising MusicGen. Music samples, code, and models are available at https://github.com/facebookresearch/audiocraft

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 3 repositories linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: named in the paper: 3 samples from 1 repository, 3 ran (0 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 15 samples from 2 repositories, 12 ran (7 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 15 samples that ran has no recorded date.

facebookresearch/audiocraft mentioned in paperpytorchMITSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
atharva20038/music4all mentioned on GitHubjaxSyntology: not harvested report
collabora/whisperspeech mentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (2 instrument-failed) · 1 unverified report
theodorblackbird/lina-speech mentioned on GitHubpytorchSyntology: 7 samples, 5 ran (3 instrument-failed) · 2 unverified report
whisperspeech/whisperspeech mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robust Speech Recognition via Large-Scale Weak Supervision (arXiv:2212.04356; that paper's own run record: 49 ran (of which 0 constructed an object rather than computing a result; 36 with no instrument failure: 4 honoured, 1 violated, 31 with no contract checked; 13 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
pwc-1/Paper-5 mindsporeSyntology: not harvested report
pwc-1/Paper-5 mindsporeSyntology: not harvested report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

18 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong
2ran; the contract check could not run
7ran
3unverified

Licence: 9 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

facebookresearch/audiocraft named in the paper 3 samples, 3 ran (3 instrument-failed) · 0 unverified
get_adv_criterion audiocraft/adversarial/losses.py ran · our draft was wrong MIT (permissive) · b94d3dcb2a918be3 · report fixture: signature loss_type:str/0/str · returned function · level recorded 2026-09-24
get_fake_criterion audiocraft/adversarial/losses.py ran · our draft was wrong MIT (permissive) · 88b0022a7cb492a1 · report fixture: signature loss_type:str/0/str · returned function · level recorded 2026-09-24
get_real_criterion audiocraft/adversarial/losses.py ran · our draft was wrong MIT (permissive) · 31e35a10d885d5a5 · report fixture: signature loss_type:str/0/str · returned function · level recorded 2026-09-24
collabora/whisperspeech community (archive-listed) 8 samples, 7 ran (2 instrument-failed) · 1 unverified
calc_len whisperspeech/extract_spk_emb.py ran MIT (permissive) · 4cbe50f8df8999aa · report fixture: signature x:dict/0/? · returned dict · level recorded 2026-09-24
load_model in 479 papers whisperspeech/inference.py ran MIT (permissive) · e03ec9babe137321 · report fixture: signature ref:str/0/str, spec:NoneType/0/?, device:str/0/str, cache_dir:NoneType/0/? · returned Tensor · level recorded 2026-09-24
logits_to_probs in 18 papers whisperspeech/inference.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 8a8edc42e5e25cea · report fixture: signature logits:Tensor/2/float, T:float/0/float, top_k:int/0/int · returned Tensor · level recorded 2026-09-22
multinomial_sample_one_no_sync in 10 papers whisperspeech/inference.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 0b5f90e8856ad7af · report fixture: signature probs_sort:Tensor/2/float · returned Tensor · level recorded, date not recorded
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
whisperspeech/modules.py ran fingerprinted MIT (permissive) · 72ac2b9f11df2bb5 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
sinusoids in 13 papers whisperspeech/modules.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · a314b3fcba001058 · report fixture: signature length:int/0/int, channels:int/0/int, max_timescale:int/0/int · returned Tensor · level recorded 2026-09-24
to_id whisperspeech/languages.py ran MIT (permissive) · e67183981542ea8a · report fixture: signature lang:str/0/str · returned int · level recorded 2026-09-25
rope_rotate whisperspeech/modules.py unverified MIT (permissive) · 97b1bc4db972b9ca · report
theodorblackbird/lina-speech community (archive-listed) 7 samples, 5 ran (3 instrument-failed) · 2 unverified
MultiEmbedding model/lina.py ran licence not identified · pointer only · d7c009ddcc0fa372 · report fixture: signature idx:Tensor/2/int · returned Tensor · level recorded 2026-09-24
MulticlassAccuracy model/lina.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 545e144abdc0bc99 · report fixture: signature preds:Tensor/2/float, targets:Tensor/1/int · returned Tensor · level recorded 2026-09-22
sequence_mask in 55 papers
census: 12 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
model/lina.py ran · our draft was wrong licence not identified · pointer only · 7286741cac3a2cab · report fixture: signature lengths:Tensor/1/int, max_len:NoneType/0/?, device:device/0/? · returned Tensor · level recorded 2026-09-22
topk_sampling in 8 papers model/lina.py ran · our draft was wrong licence not identified · pointer only · 9c43cea8408f44fb · report fixture: signature seq:Tensor/2/float, k:int/0/int, temp:float/0/float · returned Tensor · level recorded 2026-09-24
undelay_rvq model/lina.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 84caf63d220bcde1 · report fixture: signature extended_code:Tensor/3/float · returned Tensor · level recorded 2026-09-22
AttentiveRNN model/lina.py unverified licence not identified · pointer only · c1ae840cb12e7690 · report
Lina model/lina.py unverified licence not identified · pointer only · b16dd7e91ff0ea1c · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for MUSICGEN (graph method: MUSICGEN). 8 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. Lina entry · level 0 · unverified · b16dd7e91ff0ea1c
  2. AttentiveRNN model · level 0 · unverified · c1ae840cb12e7690
  3. MultiEmbedding helper · level 1 · ran · d7c009ddcc0fa372
  4. MulticlassAccuracy helper · level 1 · ran · 545e144abdc0bc99
  5. exists helper · level 1 · ran · violated contract · 608e364a9d2376a3
  6. sequence_mask helper · level 1 · ran · our draft was wrong · 7286741cac3a2cab
  7. topk_sampling helper · level 1 · ran · our draft was wrong · 9c43cea8408f44fb
  8. undelay_rvq helper · level 1 · ran; the contract check could not run (RAISES) · 84caf63d220bcde1

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2306.05284") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingMusic GenerationText-to-Music Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Music Generation MusicCaps MusicGen w/o melody (1.5B) FAD 3.4 #10 of 21 Archive leaderboard report
Text-to-Music Generation MusicCaps MusicGen w/o melody (1.5B) KL_passt 1.23 #10 of 21 Archive leaderboard report
Text-to-Music Generation MusicCaps MusicGen w/o melody (3.3B) FAD 3.8 #13 of 21 Archive leaderboard report
Text-to-Music Generation MusicCaps MusicGen w/o melody (3.3B) FD_openl3 197.12 #13 of 21 Archive leaderboard report
Text-to-Music Generation MusicCaps MusicGen w/o melody (3.3B) KL_passt 1.31 #13 of 21 Archive leaderboard report
Text-to-Music Generation MusicCaps MusicGen w/ random melody (1.5B) FAD 5.0 #16 of 21 Archive leaderboard report
Text-to-Music Generation MusicCaps MusicGen w/ random melody (1.5B) KL_passt 1.31 #16 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections