RK's repositories
Azerbaijani-Text-Converters
Azerbaijani keyboard layout converter scripts collections.
CMGAN
Conformer-based Metric GAN for speech enhancement
DeepFaceLive
Real-time face swap for PC streaming or video calls
inference_service
A wrapper to connect client code to wav2vec model inference service.
install-tesseract-redhat-centos
Script for downloading and installing Tesseract OCR Engine on RedHat and CentOS
KenLM-training
Training an n-gram based Language Model using KenLM toolkit for Deep Speech 2
LLM-Book
This book is a comprehensive manual designed to empower professionals to harness the potential of AI technologies responsibly and innovatively. The book addresses the technical, ethical, and practical aspects of AI development, offering a roadmap for those looking to advance in the rapidly evolving field of LLM Ops.
mimic2
Text to Speech engine based on the Tacotron architecture, initially implemented by Keith Ito.
mycroft-precise
A lightweight, simple-to-use, RNN wake word listener
nemoexamples
Experiments with NVIDIA NeMo
ngram-lm-wiki
Scripts to train a n-gram language models on Wikipedia articles
roman_converter
roman_converter is a Python package for converting between Roman numerals and integers. It provides functionality to convert integers to Roman numerals and vice versa. Additionally, it can parse numbers written in words and convert them to Roman numerals.
self-supervised-speech-recognition
speech to text with self-supervised learning based on wav2vec 2.0 framework
tacotron2
Multispeaker & Emotional TTS based on Tacotron 2 and Waveglow
uncaptcha3
Update of uncaptcha2 from 2019
vakyansh-wav2vec2-experimentation
Repository containing experimentation platform on how to train, infer on wav2vec2 models.
wav2vec-toolkit
A collection of scripts to preprocess ASR datasets and finetune language-specific Wav2Vec2 XLSR models
wer_are_we
Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.
zabbix-template-rclone
Monitoring rclone sync tasks
zabbix-template-speedtest
Monitoring internet bandwidth using speedtest and zabbix
zamia-speech
Open tools and data for cloudless automatic speech recognition