Yehor Smoliakov

simple-django-login-and-register. An example of Django project with basic user functionality.

speech-recognition-uk. 🇺🇦 Speech Recognition & Synthesis for Ukrainian

openapi3-generator. A generator for OpenAPI 3

ukrainian-tts-datasets. 🇺🇦 Open Source Ukrainian Text-to-Speech datasets

asr-corpus-creator. This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.

whisper-ukrainian. Trainer and Evaluation scripts for fine-tuning Whisper models for the Ukrainian language

NLLB-Translator. Python

ua-silero-demo. Speech-to-Text for the Ukrainian language based on Silero

ukrainian-accentor. Add accents to words in the Ukrainian language

qirimtatar-tts-datasets. Open Source Crimean Tatar Text-to-Speech datasets

libra-grpc-py. gRPC client for Libra in Python

tts_uk. High-fidelity speech synthesis for Ukrainian using modern neural networks.

optimized-whisper. Use quantized versions of Whisper to speed up inference

audio-katana. A tool to slice your audio files into chunks using the Voice Activity Detection technique

diagrams-telephony. Classes of Telephony for the Python's diagrams package

fail2ban-scripts. This is a simple python code to get the list of banned IP addresses from Fail2ban

rfeed. Extensible RSS 2.0 Feed Generator written in Python

django-encore. Django integration with Webpack Encore

ukrainian-stt-bot. Telegram bot for Ukrainian Speech-to-Text

wav2vec2-uk-demo. Demo of Ukrainian wav2vec2 model

radtts-hifigan. RADTTS + HiFiGAN vocoder

flashlight-ukrainian. The Ukrainian Acoustic Model for Flashlight

feedly_search. Utility for search RSS feeds on https://feedly.com

kvm-over-ip-cn8000a-jnlp-client. The instruction that helps you to run the Java Client from ATEN's software "KVM over IP"

test-wav2vec2-by-microphone. A small script to test wav2vec2 models using a microphone

vosk-ukrainian-demo. VOSK demo for the Ukrainian language

radtts-uk. 🇺🇦 Ukrainian RAD-TTS++ models (decoder + models with 3 voices) and HiFiGAN model

oberon-cgi. The answer to a question: "How to use Oberon in the Web?"

ukrainian-onnx-model. An ONNX model for speech recognition of the Ukrainian language

cv10-uk-testset-clean. The cleaned Common Voice 10 (test set) that has been checked by a human for Ukrainian 🇺🇦

share-image-server. A generation server for preview images

voicefilter. Inference part of VoiceFilter

useful-stuff. Scripts, configs, docker files, commands which are useful

tts-silero-bot. This Telegram bot shows Silero TTS

w2v2-bert-aligner. Aligner for wav2vec2-bert models

wmsigner. WebMoney Signer для Python

radtts. Provides training, inference and voice conversion recipes for RADTTS and RADTTS++: Flow-based TTS models with Robust Alignment Learning, Diverse Synthesis, and Generative Modeling and Fine-Grained Control over of Low Dimensional (F0 and Energy) Speech Attributes.

simple-django-login-and-register-dynamic-lang. An example of Django project with basic user functionality with dynamic language

keyllm. Extract keywords using LLMs

wav2vec2-jit. Export a traced JIT version of wav2vec2 models

awesome-ukrainian-nlp. Curated list of Ukrainian natural language processing (NLP) resources (corpora, pretrained models, libriaries, etc.)

radtts-istftnet. RADTTS + iSTFTNet vocoder

CleanUNet. Packaged CleanUNet

privatbank-send-money. Простой скрипт для отправки денег в ПриватБанке через Мерчант API

rust-learning. My learning notes about Rust

asr-datasets-cleaner. A pipeline to make ASR datasets better

lang-detector-bot. Telegram bot for language detection from Voice based on Silero VAD

analyse-audio-languages. Audio analysis for used languages

iSTFTNet-pytorch. Patched original code with some developer additions, don't use in prod

rVADfast. This is the Python library for an unsupervised, fast method for robust voice activity detection (rVAD), as in the paper rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method.

argilla-audio-annotation. Audio Annotation in Argilla - a python script creates an audio dataset to the Argilla instance

r-with-gradio. Use R with Gradio

ukrainian-radtts. Text-to-Speech for Ukrainian using NVIDIA's RADTTS