Alexander Veysov

silero-vad. Silero VAD: pre-trained enterprise-grade Voice Activity Detector

silero-models. Silero Models: pre-trained text-to-speech models made embarrassingly simple

open_stt. Open STT

silero-stress. Silero Stress — pre-trained enterprise-grade automated stress and homograph disambiguation for the Russian language

russian_stt_text_normalization. Russian text normalization pipeline for speech-to-text and other applications based on tagging s2s networks

ds_bowl_2018. Kaggle Data Science Bowl 2018

spacenet-three. Space Net Three Competition code

playing_with_vae. Comparing FC VAE / FCN VAE / PCA / UMAP on MNIST / FMNIST

msc-2018-final. Python

mnasnet-pytorch. A PyTorch implementation of MNASNET

gpu-box-setup. Dockerfile

deepspeech.pytorch. Speech Recognition using DeepSpeech2.

emoji-sentiment-dataset.

cft-contest-2018. Repository with illustrations for cft-contest-2018

awesome_doom_quickstart. Many young people have not played doom ... this is a small guide to help them start their journey

jungle-dd-av-sk. Jupyter Notebook

open-speech-corpora. A list of accessible speech corpora for ASR, TTS, and other Speech Technologies

emoji_sentiment. Python

spacenet-three-topcoder. Jupyter Notebook

speechbrain. A PyTorch-based Speech Toolkit

coolgpus. GPU fan control for headless Linux

MNASNet-pytorch-1. MNASNet implementation and pre-trained model in PyTorch

electricity_forecast. Jupyter Notebook

albumentations. fast image augmentation library and easy to use wrapper around other libraries

pyst2. A fork of the famous python pyst library for Asterisk.

hifi-gan. HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

pyarmor. A tool used to obfuscate python scripts, bind obfuscated scripts to fixed machine or expire obfuscated scripts.

fish-ssd. My ssd tinkering for fish classification

models. A collection of pre-trained, state-of-the-art models in the ONNX format

speech-recognition-uk. Speech Recognition for Ukrainian

mobile_demo. JavaScript

F5-TTS. Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"