Papers › The PyTorch-Kaldi Speech Recognition Toolkit

The PyTorch-Kaldi Speech Recognition Toolkit

19 Nov 2018arXiv:1811.07453archive 2025-07-28

Mirco Ravanelli, Titouan Parcollet, Yoshua Bengio

The availability of open-source software is playing a remarkable role in the popularization of speech recognition and deep learning. Kaldi, for instance, is nowadays an established framework used to develop state-of-the-art speech recognizers. PyTorch is used to build neural networks with the Python language and has recently spawn tremendous interest within the machine learning community thanks to its simplicity and flexibility. The PyTorch-Kaldi project aims to bridge the gap between these popular toolkits, trying to inherit the efficiency of Kaldi and the flexibility of PyTorch. PyTorch-Kaldi is not only a simple interface between these software, but it embeds several useful features for developing modern speech recognizers. For instance, the code is specifically designed to naturally plug-in user-defined acoustic models. As an alternative, users can exploit several pre-implemented neural networks that can be customized using intuitive configuration files. PyTorch-Kaldi supports multiple feature and label streams as well as combinations of neural networks, enabling the use of complex neural architectures. The toolkit is publicly-released along with a rich documentation and is designed to properly work locally or on HPC clusters. Experiments, that are conducted on several datasets and tasks, show that PyTorch-Kaldi can effectively be used to develop modern state-of-the-art speech recognizers.

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 6 code samples harvested from 2 repositories linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 3 ran (2 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.

mravanelli/pytorch-kaldi officialmentioned in papermentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
Baileyswu/pytorch-hmm-vae mentioned on GitHubpytorchSyntology: not harvested report
Dahee96/Seq2seq- mentioned on GitHubpytorchSyntology: not harvested report
NOEPG/pytorch-kaldi mentioned on GitHubpytorchSyntology: not harvested report
PeiyanFlying/https-github.com-PeiyanFlying-pytorch-kaldi mentioned on GitHubpytorchSyntology: not harvested report
amikey/pytorch-kaldi mentioned on GitHubpytorchSyntology: not harvested report
ayyucedemirbas/gcommands_12_classes mentioned on GitHubpytorchSyntology: not harvested report
walterheymans/pytorch-kaldi-gan mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
wponghiran/imp-snns-for-sl mentioned on GitHubpytorchSyntology: not harvested report
xpz123/pytorch-kaldi mentioned on GitHubpytorchSyntology: not harvested report
yrhvivian/pytorch-kaldi mentioned on GitHubpytorchSyntology: 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

6 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures 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.

2ran · honoured contract
3ran · our draft was wrong
1unverified

Licence: 6 of the 6 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 2 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.

mravanelli/pytorch-kaldi official repository 3 samples, 2 ran (2 instrument-failed) · 1 unverified
convert_numpy_to_torch core.py ran · our draft was wrong no licence file found · pointer only · e6b30d748e337e88 · report fixture: signature data_set_dict:dict/0/?, save_gpumem:bool/0/bool, use_cuda:bool/0/bool · returned tuple · level recorded 2026-09-22
extract_data_from_shared_list core.py ran · our draft was wrong fingerprinted no licence file found · pointer only · c6c35455d3c22ed7 · report fixture: signature shared_list:list/1/str · returned tuple · level recorded 2026-09-22
Glorot kaldi_decoding_scripts/utils/nnet/make_nnet_proto.py unverified no licence file found · pointer only · 01273488da5e2f47 · report
walterheymans/pytorch-kaldi-gan community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
format_time in 140 papers train_gan.py ran · our draft was wrong fingerprinted no licence file found · pointer only · cbb514194a31ad91 · report fixture: signature time_in_seconds:float/0/float · returned str · level recorded 2026-09-22
get_labels in 42 papers train_gan.py ran · honoured contract no licence file found · pointer only · f5fb92f12ec49482 · report fixture: signature bs:int/0/int, label:int/0/int · returned Tensor · level recorded 2026-09-22
get_pearson_correlation train_gan.py ran · honoured contract fingerprinted no licence file found · pointer only · 768014045bed0615 · report fixture: signature tensor1:Tensor/2/float, tensor2:Tensor/2/float · returned float32 · level recorded 2026-09-22

Tasks

Distant Speech RecognitionNoisy Speech RecognitionSpeech Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Distant Speech Recognition DIRHA English WSJ Li-GRU Word Error Rate (WER) 23.9 #1 of 3 Archive leaderboard report
Noisy Speech Recognition CHiME real Li-GRU Percentage error 14.6 #3 of 5 Archive leaderboard report
Speech Recognition LibriSpeech test-clean Li-GRU Word Error Rate (WER) 6.2 #60 of 64 Archive leaderboard report
Speech Recognition TIMIT LiGRU + Dropout + BatchNorm + Monophone Reg Percentage error 14.2 #3 of 22 Archive leaderboard report
Speech Recognition TIMIT LSTM + Dropout + BatchNorm + Monophone Reg Percentage error 14.5 #4 of 22 Archive leaderboard report
Speech Recognition TIMIT GRU + Dropout + BatchNorm + Monophone Reg Percentage error 14.9 #6 of 22 Archive leaderboard report
Speech Recognition TIMIT RNN + Dropout + BatchNorm + Monophone Reg Percentage error 15.9 #8 of 22 Archive leaderboard report
Speech Recognition TIMIT LSTM Percentage error 16.0 #9 of 22 Archive leaderboard report
Speech Recognition TIMIT Li-GRU Percentage error 16.3 #10 of 22 Archive leaderboard report
Speech Recognition TIMIT RNN Percentage error 16.5 #12 of 22 Archive leaderboard report
Speech Recognition TIMIT GRU Percentage error 16.6 #13 of 22 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