Papers › Spirit LM: Interleaved Spoken and Written Language Model

Spirit LM: Interleaved Spoken and Written Language Model

8 Feb 2024arXiv:2402.05755archive 2025-07-28

Tu Anh Nguyen, Benjamin Muller, Bokai Yu, Marta R. Costa-Jussa, Maha Elbayad, Sravya Popuri, Christophe Ropers, Paul-Ambroise Duquenne, Robin Algayres, Ruslan Mavlyutov, Itai Gat, Mary Williamson, Gabriel Synnaeve, Juan Pino, Benoit Sagot, Emmanuel Dupoux

We introduce Spirit LM, a foundation multimodal language model that freely mixes text and speech. Our model is based on a 7B pretrained text language model that we extend to the speech modality by continuously training it on text and speech units. Speech and text sequences are concatenated as a single stream of tokens, and trained with a word-level interleaving method using a small automatically-curated speech-text parallel corpus. Spirit LM comes in two versions: a Base version that uses speech phonetic units (HuBERT) and an Expressive version that models expressivity using pitch and style units in addition to the phonetic units. For both versions, the text is encoded with subword BPE tokens. The resulting model displays both the semantic abilities of text models and the expressive abilities of speech models. Additionally, we demonstrate that Spirit LM can learn new tasks in a few-shot fashion across modalities (i.e. ASR, TTS, Speech Classification). We make available model weights and inference code.

PaperPDFCodeCode Syntology ran

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 1 code sample harvested from 1 repository linked to this paper: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 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.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/spiritlm officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified 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.

Code Syntology ran Syntology

1 sample harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong

Licence: 1 of the 1 sample is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from facebookresearch/spiritlm. “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.

facebookresearch/spiritlm official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
load_pred spiritlm/eval/eval_stsp.py ran · our draft was wrong licence not identified · pointer only · 8687b6ac8f6c5823 · report fixture: signature predictions:str/0/str · returned dict · level recorded 2026-09-22

Tasks

Language ModelingLanguage Modellingmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling 2000 HUB5 English MMLU 10-stage average accuracy 10 #1 of 1 Archive leaderboard report
Language Modelling SALMon Spirit-LM (Expr.) Background (Domain) Consistency 55.0 #1 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (Expr.) Background (Random) Consistency 64.0 #1 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (Expr.) Background Alignment 59.5 #1 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (Expr.) Gender Consistency 85.0 #1 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (Expr.) Room Consistency 54.5 #1 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (Expr.) Sentiment Alignment 52.0 #1 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (Expr.) Sentiment Consistency 73.5 #1 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (Expr.) Speaker Consistency 81.0 #1 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (base) Background (Domain) Consistency 53.5 #9 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (base) Background (Random) Consistency 55.5 #9 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (base) Background Alignment 51.5 #9 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (base) Gender Consistency 67.0 #9 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (base) Room Consistency 54.5 #9 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (base) Sentiment Alignment 48.0 #9 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (base) Sentiment Consistency 54.5 #9 of 10 Archive leaderboard report
Language Modelling SALMon Spirit-LM (base) Speaker Consistency 69.5 #9 of 10 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.

Methods

BASEBPESET

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