A toolkit for speaker diarization.

T-one is a high-performance streaming ASR pipeline for Russian, specialized for the telephony domain.

VOSK Speech Recognition Toolkit

A Conversational Speech Generation Model

Russian speech technology links

YSDA course in Speech Processing.

Deep Learning for Speech

DeepPavlov Dream is a free, open-source Multiskill AI Assistant Platform built using DeepPavlov Conversational AI Stack. It is built on top of DeepPavlov Agent running as container in Docker. It ru…

Telegram bot for weightlifters that calculates one-rep max (1RM) from multi-rep weight and vice versa.

SOVA DC - service for decentralized SOVA ASR/SOVA TTS computing in a distributed network

Conversational AI Benchmark.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Deep learning for audio processing

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

SOVA Voice Studio

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

NLP-preprocessor for the SOVA-TTS project

Tacotron2 based engine for the SOVA-TTS project

SOVA ASR (Automatic Speech Recognition)

Dialog Processor

Demo of CK widget with standart functionality

Open Source React Chat Widget. Ready for use and can be connected to any backend like Chatbot/NLP/Live Chat engine or messenger.

CK Dialog Language module