Papers › SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models

SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models

31 Aug 2023arXiv:2308.16692archive 2025-07-28

Xin Zhang, Dong Zhang, ShiMin Li, Yaqian Zhou, Xipeng Qiu

Current speech large language models build upon discrete speech representations, which can be categorized into semantic tokens and acoustic tokens. However, existing speech tokens are not specifically designed for speech language modeling. To assess the suitability of speech tokens for building speech language models, we established the first benchmark, SLMTokBench. Our results indicate that neither semantic nor acoustic tokens are ideal for this purpose. Therefore, we propose SpeechTokenizer, a unified speech tokenizer for speech large language models. SpeechTokenizer adopts the Encoder-Decoder architecture with residual vector quantization (RVQ). Unifying semantic and acoustic tokens, SpeechTokenizer disentangles different aspects of speech information hierarchically across different RVQ layers. Furthermore, We construct a Unified Speech Language Model (USLM) leveraging SpeechTokenizer. Experiments show that SpeechTokenizer performs comparably to EnCodec in speech reconstruction and demonstrates strong performance on the SLMTokBench benchmark. Also, USLM outperforms VALL-E in zero-shot Text-to-Speech tasks. Code and models are available at https://github.com/ZhangXInFD/SpeechTokenizer/.

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 26 code samples: 24 from 3 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 26: 24 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 5 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 23 samples from 2 repositories, 21 ran (13 with no instrument failure; 8 where Syntology's instrument failed); community: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 24 samples that ran have no recorded date.

0nutation/uslm officialmentioned in papermentioned on GitHubpytorchSyntology: 7 samples, 7 ran (3 instrument-failed) · 0 unverified report
zhangxinfd/speechtokenizer officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 16 samples, 14 ran (5 instrument-failed) · 2 unverified report
0nutation/slmtokbench officialmentioned in paperSyntology: not harvested 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

26 samples harvested: 24 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 5 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 2 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.

1ran · honoured contract
5ran · violated contract
5ran · our draft was wrong
3ran; the contract check could not run
10ran
2unverified

Licence: 10 of the 26 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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. 2 samples are listed last, in a group without a repository. “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.

0nutation/uslm official repository 7 samples, 7 ran (3 instrument-failed) · 0 unverified
calc_lr modules/scheduler.py ran fingerprinted no licence file found · pointer only · ffec7b2aa35d0253 · report fixture: signature step:int/0/int, dim_embed:int/0/int, warmup_steps:int/0/int · returned float · level recorded 2026-09-24
circular_padding bin/infer.py ran fingerprinted no licence file found · pointer only · 6c54df5029e831e1 · report fixture: signature x:Tensor/3/float, tgt_len:int/0/int · returned Tensor · level recorded 2026-09-24
random_cast_to_half modules/scaling.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 982b9083b5a41368 · report fixture: signature x:Tensor/2/float, min_abs:float/0/float · returned Tensor · level recorded 2026-09-24
random_clamp modules/scaling.py ran no licence file found · pointer only · 1d72f492e19080e6 · report fixture: signature x:Tensor/2/float, min:float/0/float, max:float/0/float, prob:float/0/float, reflect:float/0/float · returned Tensor · level recorded 2026-09-24
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket
modules/scaling.py ran · our draft was wrong fingerprinted no licence file found · pointer only · c124aa8bd6b9ebe9 · report fixture: signature x:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-24
top_k_top_p_filtering in 96 papers
census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
models/valle.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 99a311d99448f881 · report fixture: signature logits:Tensor/2/float, top_k:int/0/int, top_p:float/0/float, filter_value:float/0/float, min_tokens_to_keep:int/0/int · returned Tensor · level recorded 2026-09-24
topk_sampling in 8 papers models/valle.py ran no licence file found · pointer only · fb8e21d446dcf26f · report fixture: signature logits:Tensor/2/float, top_k:int/0/int, top_p:float/0/float, temperature:float/0/float · returned Tensor · level recorded 2026-09-24
zhangxinfd/speechtokenizer official repository 16 samples, 14 ran (5 instrument-failed) · 2 unverified
apply_parametrization_norm in 7 papers speechtokenizer/modules/conv.py ran · our draft was wrong Apache-2.0 (permissive) · 6c82cd3d9b6dba51 · report fixture: signature module:callable/0/?, norm:str/0/str · returned Conv2d · level recorded 2026-09-26
average_metrics speechtokenizer/quantization/distrib.py ran Apache-2.0 (permissive) · 18804e5e23d7209a · report fixture: signature metrics:dict/0/?, count:float/0/float · returned dict · level recorded 2026-09-24
build_stable_quantized_cdf speechtokenizer/quantization/ac.py ran Apache-2.0 (permissive) · b9d6342963694f46 · report fixture: signature pdf:Tensor/1/float, total_range_bits:int/0/int, roundoff:float/0/float, min_range:int/0/int, check:bool/0/bool · returned Tensor · level recorded 2026-09-24
collate_fn in 500 papers speechtokenizer/trainer/dataset.py ran Apache-2.0 (permissive) · 2f77684a19a01429 · report fixture: signature data:list/1/tuple · returned tuple · level recorded 2026-09-24
default in 430 papers speechtokenizer/quantization/core_vq.py ran · our draft was wrong Apache-2.0 (permissive) · 1e8f03292b45230b · report fixture: signature val:NoneType/0/?, d:str/0/str · returned str · level recorded 2026-09-22
dynamic_range_compression_torch in 9 papers speechtokenizer/trainer/loss.py ran fingerprinted Apache-2.0 (permissive) · 6f6051e1e48db824 · report fixture: signature x:Tensor/2/float, C:int/0/int, clip_val:float/0/float · returned Tensor · level recorded 2026-09-24
get_2d_padding speechtokenizer/discriminators.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 35ac4a3a2d0faeac · report fixture: signature kernel_size:tuple/1/int, dilation:tuple/1/int · returned tuple · level recorded 2026-09-26
get_dataloader in 111 papers speechtokenizer/trainer/dataset.py ran Apache-2.0 (permissive) · 9f134f4ea526149a · report fixture: signature ds:SimpleDataset/0/?, batch_size:int/0/int, shuffle:bool/0/bool, num_workers:int/0/int · returned DataLoader · level recorded 2026-09-24
get_extra_padding_for_conv1d in 9 papers speechtokenizer/modules/conv.py ran · our draft was wrong Apache-2.0 (permissive) · 8d9aa381c6147164 · report fixture: signature x:Tensor/3/float, kernel_size:int/0/int, stride:int/0/int, padding_total:int/0/int · returned int · level recorded 2026-09-26
get_padding in 84 papers speechtokenizer/discriminators.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · a26f85d7c72ef39a · report fixture: signature kernel_size:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22
laplace_smoothing in 8 papers
census: 3 implementations from 6 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind float, dtype float32
speechtokenizer/quantization/core_vq.py ran · violated contract Apache-2.0 (permissive) · c360b5ccff704a88 · report fixture: signature x:Tensor/1/float, n_categories:int/0/int, epsilon:float/0/float · returned Tensor · level recorded 2026-09-22
sample_vectors in 15 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
speechtokenizer/quantization/core_vq.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 09f10cd96592b37d · report fixture: signature samples:Tensor/2/float, num:int/0/int · returned Tensor · level recorded 2026-09-22
snake in 10 papers speechtokenizer/modules/seanet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · f247e4748f379a76 · report fixture: returned Tensor · level recorded 2026-09-22
spectral_normalize_torch in 8 papers speechtokenizer/trainer/loss.py ran fingerprinted Apache-2.0 (permissive) · bcadb9daef59d785 · report fixture: signature magnitudes:Tensor/2/float · returned Tensor · level recorded 2026-09-24
all_reduce in 42 papers speechtokenizer/quantization/distrib.py unverified Apache-2.0 (permissive) · 193e4cb06c7034a4 · report
get_norm_module in 6 papers speechtokenizer/modules/conv.py unverified Apache-2.0 (permissive) · 9b33ed59d8d8736e · report
ZhangXInFD/soundstorm-speechtokenizer community 1 sample, 1 ran (0 instrument-failed) · 0 unverified
divisible_by in 33 papers soundstorm_speechtokenizer/soundstorm.py ran · violated contract fingerprinted MIT (permissive) · 856d86b39c6005b4 · report fixture: signature numer:int/0/int, denom:int/0/int · returned bool · level recorded, date not recorded
Repository not located 2 samples, 2 ran (0 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
default in 430 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · 60fff7c3c400d7ff · report fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
repository not located ran · violated contract licence of this copy not recorded · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded

Tasks

DecoderLanguage ModelingLanguage ModellingQuantizationText to Speechtext-to-speech

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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