ichDaheim/misaki
G2P
born: a long time ago/ living: last time i checked: yes / death: not yet. will update on status change ;-)
G2P
This project provides a complete, documented training recipe for fine-tuning Kokoro-82M on a new language. In this case German
zero-shot voice conversion & singing voice conversion, with real-time support
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
VibeVoice Community Fork: Long-form conversational TTS
Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)
HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform
Frontier Open-Source Text-to-Speech
Official Implementation of StyleTTS
SOTA Open Source TTS
train wake word models
Fast Streaming TTS with Orpheus + WebRTC (with FastRTC)
prime is a framework for efficient, globally distributed training of AI models over the internet.
Begleitmaterial zum Workshop "Eigene Sprachmodelle"
An open-source audio wake word (or phrase) detection framework with a focus on performance and simplicity.
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
A lightweight, simple-to-use, RNN wake word listener
Free models for precise-lite
tflite GRU VAD detector
🐸 - A general purpose model trainer, as flexible as it gets