Simple python lib to tokenize texts into sentences and sentences to words. Small, fast and robust. Comes with ukrainian flavour

Partial python port of java SRX segmenter

Ukrainian text normalization and tokenization utilities

Native offline Qwen3-TTS for desktop

Open Source Speech Language Model

MichiAI: A Low Latency, Full Duplex Speech LLM with zero coherence loss

[ICASSP 2026]Official code for "Prosody-Guided Harmonic Attention for Phase-Coherent Neural Vocoding in the Complex Spectrum"

OLaPh (Optimal Language Phonemizer) is a multilingual phonemization framework that converts text into phonemes surpassing the quality of comparable frameworks.

Pure bfloat AdamW+ tweaks

Soprano: Instant, Ultra-Realistic Text-to-Speech

This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"

[INTERSPEECH 2026 Oral]Official code for "Semantic-VAE: Semantic-Alignment Latent Representation for Better Speech Synthesis"

Training code and dataset cleasing with Sidon

Fast and accurate fundamental frequency (F0) detector using convolutional neural networks

A random walk voice style cloning application for Kokoro text to speech

StyleTTS2 + Vocos as a Decoder

A Toolkit to Help Optimize Onnx Model

Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.

🇺🇦 Speech Recognition & Synthesis for Ukrainian

Noise reduction in python using spectral gating (speech, bioacoustics, audio, time-domain signals)

Arbitrary-steps Image Super-resolution via Diffusion Inversion (CVPR 2025)

This is the M-AILABS Speech Dataset