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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2308.16692")

Code

Syntology Ran 21 of 26 code samples harvested from 3 repositories linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · honoured contract; 4 ran · violated contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 13 ran with no contract checked.

By repository: official repository: 23 samples from 2 repositories, 18 ran; community: 1 sample from 1 repository, 1 ran; 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.

0nutation/uslm officialmentioned in papermentioned on GitHubpytorch report
zhangxinfd/speechtokenizer officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
0nutation/slmtokbench officialmentioned in paper 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; 21 ran; 1 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
4ran · violated contract
1ran · our draft was wrong
2ran · fixture could not drive it
13ran
5unverified

Licence: 9 of the 26 samples are 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 3 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

average_metrics ZhangXInFD/SpeechTokenizer/speechtokenizer/quantization/distrib.py official repository ran Apache-2.0 (permissive) · 18804e5e23d7209a · report
build_stable_quantized_cdf ZhangXInFD/SpeechTokenizer/speechtokenizer/quantization/ac.py official repository ran Apache-2.0 (permissive) · b9d6342963694f46 · report
calc_lr 0nutation/uslm/modules/scheduler.py official repository ran fingerprinted no licence file found · pointer only · ffec7b2aa35d0253 · report
circular_padding 0nutation/uslm/bin/infer.py official repository ran fingerprinted no licence file found · pointer only · 6c54df5029e831e1 · report
collate_fn ZhangXInFD/SpeechTokenizer/speechtokenizer/trainer/dataset.py official repository ran fingerprinted Apache-2.0 (permissive) · 2f77684a19a01429 · report
default ZhangXInFD/SpeechTokenizer/speechtokenizer/quantization/core_vq.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 1e8f03292b45230b · report
dynamic_range_compression_torch ZhangXInFD/SpeechTokenizer/speechtokenizer/trainer/loss.py official repository ran fingerprinted Apache-2.0 (permissive) · 6f6051e1e48db824 · report
get_dataloader ZhangXInFD/SpeechTokenizer/speechtokenizer/trainer/dataset.py official repository ran Apache-2.0 (permissive) · 9f134f4ea526149a · report
get_padding ZhangXInFD/SpeechTokenizer/speechtokenizer/discriminators.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · a26f85d7c72ef39a · report
laplace_smoothing ZhangXInFD/SpeechTokenizer/speechtokenizer/quantization/core_vq.py official repository ran · violated contract Apache-2.0 (permissive) · c360b5ccff704a88 · report
random_cast_to_half 0nutation/uslm/modules/scaling.py official repository ran fingerprinted no licence file found · pointer only · 982b9083b5a41368 · report
random_clamp 0nutation/uslm/modules/scaling.py official repository ran no licence file found · pointer only · 1d72f492e19080e6 · report
sample_vectors ZhangXInFD/SpeechTokenizer/speechtokenizer/quantization/core_vq.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 09f10cd96592b37d · report
snake ZhangXInFD/SpeechTokenizer/speechtokenizer/modules/seanet.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · f247e4748f379a76 · report
softmax 0nutation/uslm/modules/scaling.py official repository ran fingerprinted no licence file found · pointer only · c124aa8bd6b9ebe9 · report
spectral_normalize_torch ZhangXInFD/SpeechTokenizer/speechtokenizer/trainer/loss.py official repository ran fingerprinted Apache-2.0 (permissive) · bcadb9daef59d785 · report
top_k_top_p_filtering 0nutation/uslm/models/valle.py official repository ran no licence file found · pointer only · 99a311d99448f881 · report
topk_sampling 0nutation/uslm/models/valle.py official repository ran no licence file found · pointer only · fb8e21d446dcf26f · report
all_reduce ZhangXInFD/SpeechTokenizer/speechtokenizer/quantization/distrib.py official repository unverified Apache-2.0 (permissive) · 193e4cb06c7034a4 · report
apply_parametrization_norm ZhangXInFD/SpeechTokenizer/speechtokenizer/modules/conv.py official repository unverified Apache-2.0 (permissive) · 6c82cd3d9b6dba51 · report
get_2d_padding ZhangXInFD/SpeechTokenizer/speechtokenizer/discriminators.py official repository unverified Apache-2.0 (permissive) · 35ac4a3a2d0faeac · report
get_extra_padding_for_conv1d ZhangXInFD/SpeechTokenizer/speechtokenizer/modules/conv.py official repository unverified Apache-2.0 (permissive) · 8d9aa381c6147164 · report
get_norm_module ZhangXInFD/SpeechTokenizer/speechtokenizer/modules/conv.py official repository unverified Apache-2.0 (permissive) · 9b33ed59d8d8736e · report
divisible_by ZhangXInFD/soundstorm-speechtokenizer/soundstorm_speechtokenizer/soundstorm.py community ran · violated contract fingerprinted MIT (permissive) · 856d86b39c6005b4 · report
default identical code first harvested elsewhere ran · violated contract fingerprinted licence of this copy not recorded · 60fff7c3c400d7ff · report
exists identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · aa5486a3650902d8 · report

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