Papers › QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions

QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions

22 Oct 2019arXiv:1910.10261links table onlyarchive 2025-07-28

Samuel Kriman, Stanislav Beliaev, Boris Ginsburg, Jocelyn Huang, Oleksii Kuchaiev, Vitaly Lavrukhin, Ryan Leary, Jason Li, Yang Zhang

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

We propose a new end-to-end neural acoustic model for automatic speech recognition. The model is composed of multiple blocks with residual connections between them. Each block consists of one or more modules with 1D time-channel separable convolutional layers, batch normalization, and ReLU layers. It is trained with CTC loss. The proposed network achieves near state-of-the-art accuracy on LibriSpeech and Wall Street Journal, while having fewer parameters than all competing models. We also demonstrate that this model can be effectively fine-tuned on new datasets.

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="1910.10261")

Code

Syntology Ran 3 of 12 code samples harvested from 4 repositories linked to this paper; 9 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: community (archive-listed): 12 samples from 4 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

15 repositories listed; official and paper-mentioned ones first.

NVIDIA/NeMo officialmentioned in paperpytorchApache-2.0 report
isadrtdinov/quartznet mentioned on GitHubpytorch report
ivankunyankin/quartznet-asr mentioned on GitHubpytorch report
marka17/digit-recognition mentioned on GitHubpytorchMIT report
msalhab96/SpeeQ mentioned on GitHubpytorch report
nanoporetech/bonito mentioned on GitHubpytorchNOASSERTION report
oleges1/quartznet-pytorch mentioned on GitHubpytorchMIT report
osmr/imgclsmob mentioned on GitHubmxnetMIT report
sberdevices/golos mentioned on GitHubpytorch report
sooftware/OpenSpeech mentioned on GitHubpytorchMIT report
stefanpantic/asr mentioned on GitHubtfGPL-3.0 report
yangzhou6666/asrprophet mentioned on GitHubpytorch 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

12 samples harvested; 3 ran; 0 honoured the contract we drafted; 9 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.

3ran · our draft was wrong
9unverified

Licence: 2 of the 12 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 4 repositories linked to this paper, official or community; each sample names its own and says which. “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.

conv_bn_act Kirili4ik/QuartzNet-ASR-pytorch/model.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 93ea36b1e45e4172 · report
quartznet isadrtdinov/quartznet/asr/models/quartznet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 5fac3b34256008d7 · report
sepconv_bn Kirili4ik/QuartzNet-ASR-pytorch/model.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 1a3c3bbfbd73d6d8 · report
calculate_cer marka17/digit-recognition/src/utils/metrics.py community (archive-listed) unverified MIT (permissive) · 8aa28eb81f15e19e · report
convert_bytes marka17/digit-recognition/gfile.py community (archive-listed) unverified MIT (permissive) · fa009e15ffeb21b1 · report
convert_human_time marka17/digit-recognition/gfile.py community (archive-listed) unverified MIT (permissive) · 0cdbba0bc41e103e · report
download_file_from_google_drive marka17/digit-recognition/gfile.py community (archive-listed) unverified MIT (permissive) · dc1cace2b69b6f80 · report
get_act_dropout_layer oleges1/quartznet-pytorch/model/layers.py community (archive-listed) unverified MIT (permissive) · 97c5b22c22d161c6 · report
get_conv_bn_layer oleges1/quartznet-pytorch/model/layers.py community (archive-listed) unverified MIT (permissive) · c13d6372fb3fe4ad · report
get_same_padding marka17/digit-recognition/src/modules/jasper.py community (archive-listed) unverified MIT (permissive) · ba297314ad959cc0 · report
get_same_padding oleges1/quartznet-pytorch/model/utils.py community (archive-listed) unverified MIT (permissive) · 6a909b63465cabc2 · report
remove_from_dict oleges1/quartznet-pytorch/utils.py community (archive-listed) unverified MIT (permissive) · f02f10b701054ea3 · report

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition LibriSpeech test-clean QuartzNet15x5 Word Error Rate (WER) 2.69 #41 of 64 Archive leaderboard report
Speech Recognition LibriSpeech test-other QuartzNet15x5 Word Error Rate (WER) 7.25 #41 of 53 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