SoftVC VITS Singing Voice Conversion

Distribute and run LLMs with a single file.

Core Engine of Singing Voice Conversion & Singing Voice Clone

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

适配轻小说/Galgame的日中翻译大模型

[CVPR 2024] Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution

LLM training in simple, raw C/CUDA

Transcribe and translate voice into LRC file using Whisper and LLMs (GPT, Claude, et,al). 使用whisper和LLM(GPT，Claude等)来转录、翻译你的音频为字幕文件。

[SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation

High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model

Port of OpenAI's Whisper model in C/C++

21 Lessons, Get Started Building with Generative AI

Faster Whisper transcription with CTranslate2

A high-throughput and memory-efficient inference and serving engine for LLMs