Artem Gribul's repositories
SeismicNet
Seismic horizons detecting neural network
ReviewClassifier
Model and web-service for movie reviews classification and rating regression
BreaktroughHack2020
Code for digital breakgrough hackaton
allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
audiocraft
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
hifigan
An 16kHz implementation of HiFi-GAN for soft-vc.
NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
pandastyping
Type hinting for pandas DataFrame's
pflow-encodec
Implementation of TTS model based on NVIDIA P-Flow TTS Paper
pyjatka
Small-sized dataset for Keyword Spotting
ResemblyzerSlim
A python package to analyze and compare voices with deep learning (Without webrtcvad dependency)
rusynonyms
Russian words synonyms and antonyms
rwav
Just record .wav file
seamless_communication
Foundational Models for State-of-the-Art Speech and Text Translation
Trainer
🐸 - A general purpose model trainer, as flexible as it gets
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
war_survey_data
Social survey data on important topics about the war in Ukraine
wav2phonemes
Extract fake "phonemes" from pretrained wav2vec for your dataset