Yehor Smoliakov's repositories
ua-silero-demo
Speech-to-Text for the Ukrainian language based on Silero
ukrainian-accentor
Add accents to words in the Ukrainian language
test-wav2vec2-by-microphone
A small script to test wav2vec2 models using a microphone
ukrainian-onnx-model
An ONNX model for speech recognition of the Ukrainian language
wav2vec2-jit
Export a traced JIT version of wav2vec2 models
iSTFTNet-pytorch
Patched original code with some developer additions, don't use in prod
asr-corpus-by-microphone
This is a simple solution for people who want to create own corpus for Automatic Speech Recognition with just a microphone
cv10-uk-testset-clean
The cleaned Common Voice 10 (test set) that has been checked by a human for Ukrainian
ukrainian-flowtron-tts
Text-to-Speech for Ukrainian using NVIDIA's Flowtron
ukwiki-kenlm
Instruction about building a KenLM model based on Ukrainian Wikipedia data
arxiv-sanity-lite
arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors based on paper abstracts.
centrifugo-v4-redis
Dockerized Centrifugo (v4) and Redis
do-functions-php-send-email
This function gives you the ability to send email messages via any SMTP server using own predefined HTML/TXT templates.
do-functions-ukr-ner
This function gives you the ability to extract entities from text using NER
dspace-checker
A simple Go app that collects scientific articles from Dspace repos using Geziyor
egorsmkv.github.io
Some experiments
flowtron-uk-graphemes
Flowtron for Ukrainian using graphemes
php-google-merchant-feed
PHP package, that generates Google Merchant XML Feed
pyctcdecode
A fast and lightweight python-based CTC beam search decoder for speech recognition.
sgmse
Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation
sova-tts-engine
Tacotron2 based engine for the SOVA-TTS project
sova-tts-tps
NLP-preprocessor for the SOVA-TTS project
ukrainian-dspaces
DSpace instances in Ukraine
waveglow
A Flow-based Generative Network for Speech Synthesis