Kaldi Speech Recognition Toolkit

91 Last view: 2021-01-10

4 Last update: 2020-06-05

Kaldi Speech Recognition Toolkit

Kaldi

Persistent Identifier of this resource:

http://urn.fi/urn:nbn:fi:lb-2019121020

Access location: http://kaldi-asr.org/

Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers.

Kaldi is available at http://kaldi-asr.org/. An instance of Kaldi can be used in CSC's computing environment (module load kaldi).

View resource description in all available languages

Kaldi on C++-pohjainen automaattisen puheentunnistuksen työkalupakki, joka on saatavilla Apache v2.0 -lisenssillä. Kaldi on tarkoitettu etenkin puheentunnistuksen tutkijoiden käyttöön.

Kaldi on saatavilla osoitteessa http://kaldi-asr.org/. Kaldi on asennettu ja käytettävissä myös Kielipankin sovelluspalvelimella.

You don’t have the permission to edit this resource.

DistributionAvailability

Available - Unrestricted Use

Licence

Apache Licence 2.0

Download location: hidden

Distribution Access/Medium: Downloadable

Attribution Details: Katso viittausohjeet: http://kaldi-asr.org/doc/about.html. (Kielipankin sovelluspalvelimelle asennettujen Kaldi-versioiden viittausohjeet on merkitty erikseen kyseisiin kuvailutietueisiin.), Please see http://kaldi-asr.org/doc/about.html for referencing instructions. (For versions of Kaldi available via the Language Bank of Finland, please see the respective metadata descriptions.)

Contact Persons

User support at CSC - IT Center for Science Ltd. The Language Bank of Finland

User support FIN-CLARIN

toolService

Suite Of Tools

Language Independent

Input

Media type: Audio

Modality: Spoken Language, Voice

Annotation type: Speech Annotation - Orthographic Transcription

Output

Media type: Text

Annotation type: Alignment, Speech Annotation, Speech Annotation, Speech Annotation - Orthographic Transcription

Segmentation level: Phoneme, Utterance, Word

Operation

Operating system: Linux, Unix

Metadata

Created: 08/14/2017

Last Updated: 06/05/2020

Metadata Creator

Mietta Lennes

Documentation

Document Type: Other

Kaldi documentation, http://kaldi-asr.org...

Keywords: ASR, Automatic Speech Recognition, GMM, HTK, SGMM

Document Language: English

People who looked at this resource also viewed the following:

Kaldi Speech Recognition Toolkit

Kaldi

Persistent Identifier of this resource:

http://urn.fi/urn:nbn:fi:lb-2019121020

Access location: http://kaldi-asr.org/

Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers. Kaldi is available at http://kaldi-asr.org/. An instance of Kaldi can be used in CSC's computing environment (module load kaldi).

Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers.

Kaldi is available at http://kaldi-asr.org/. An instance of Kaldi can be used in CSC's computing environment (module load kaldi).