-
Novosibirsk State University
- Novosibirsk, Russia
-
14:35
(UTC +07:00) - https://www.researchgate.net/profile/Daniil-Grebenkin
Block or Report
Block or report dangrebenkin
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuse-
speech_audio_separator Public
Spliting speech WAV PCM files to fragments with use of energy signal minimums (speech pauses).
-
The code of wav2vec2 knowledge distillation hyperparameter tuning task for AINL AutoML Workshop 2024 paper
-
audio_augmentator Public
A library to make augmented audio (8/16 kHz, mono, WAV PCM) with noises corpora.
-
wav2vec2_speech_markuper Public
Automatic generation of speech dataset markup using Wav2Vec2 ASR models
-
-
-
-
speech_mail_recognition Public archive
Tool to recognize speech mail and real human. File "dictionary.cfg" is for Russian language here.
Python Apache License 2.0 UpdatedOct 16, 2021 -
audiocorpusbuilder Public archive
Command-line package for automatical creation of russian language audio corpus (pairs speech-text) from YouTube audiotracks and subtitles
-
Relative_duration_experiment Public archive
Computing relative duration for stressed vowels, non-stressed vowels in the end of the word and non-stressed vowels not in the end of the word parcing Praat TextGrid files (for Russian language aud…
Python Apache License 2.0 UpdatedNov 15, 2020