magicse

ncnn-colorization-siggraph17

ncnn-hifi-GAN

ncnn HiFi-GAN

ai-video-dubber

Aladdin-Persson-AI-Watermark-Destroy

Aladdin-Persson-AI-Watermark-Destroy Public

caffe-windows-dependencies

Build scripts to compile caffe dependencies on Windows

E2FGVI

Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

espeak-ng

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

espnet

End-to-End Speech Processing Toolkit

ggml

Tensor library for machine learning

Gyver-Lamp

Home Assistant компонент для интеграции лампы Гайвера на оригинальной прошивке

hifi-gan

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

homeassistant

LJSpeechTools

Tools for making LJSpeech datasets

McJSON

A Delphi / Lazarus / C++Builder simple and small class for fast JSON parsing.

ncnn-SpyNet-opticalflow

ncnn SpyNet opticalflow

opencv_mingw64_windows

portaudio

PortAudio is a cross-platform, open-source C language library for real-time audio input and output.

pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

radtts

Provides training, inference and voice conversion recipes for RADTTS and RADTTS++: Flow-based TTS models with Robust Alignment Learning, Diverse Synthesis, and Generative Modeling and Fine-Grained Control over of Low Dimensional (F0 and Energy) Speech Attributes.

sherpa-onnx

Speech-to-text and text-to-speech using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go

SoniTranslate

Synchronized Translation for Videos

stable-diffusion-webui-depthmap-script

High Resolution Depth Maps for Stable Diffusion WebUI

stt_normalization

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

StyleTTS

Official Implementation of StyleTTS

StyleTTS-VC

Official Implementation of StyleTTS-VC

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

uk-sherpa-onnx-model

VALL-E-X-Trainer-by-CustomData

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io

ViTA

ViTA: Video Transformer Adaptor for Robust Video Depth Estimation

voice_conversion