MaxMax2016
MaxMax2016
Computer Vision, Speech Separation, Speech Synthesis, LLMs
Languages
Repos
1351
Stars
304
Forks
242
Top Language
Python
Loading contributions...
Top Repositories
android迷你版迅雷，支持thunder:// ftp:// http:// ed2k:// 磁力链 种子文件的下载，音视频文件支持边下边播.
Huawei Grad-TTS for Chinese
SoftVC VITS Singing Voice Conversion
完全独立编译 AEC, AGC, NS, VAD in WebRTC
TTS适配器&多种
综合语音项目 Speech Toolkit for bahasa Malaysia, https://malaya-speech.readthedocs.io/
Repositories
1351android迷你版迅雷，支持thunder:// ftp:// http:// ed2k:// 磁力链 种子文件的下载，音视频文件支持边下边播.
完全独立编译 AEC, AGC, NS, VAD in WebRTC
Grapheme to phoneme conversion with deep learning.
C inference for Qwen3-ASR 0.6b and 1.7b transcriptions models
Huawei Grad-TTS for Chinese
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
A TTS that fits in your CPU (and pocket)
A lightning fast audio upsampler.
SoftVC VITS Singing Voice Conversion
The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.
TTS适配器&多种
poorman's ar-dit tts
声码器：Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-Step High-Fidelity Audio Generation
声码器：The official Implementation of PeriodWave and PeriodWave-Turbo
No description provided.
争对BigVGAN的效率优化
音高编辑器：GUI for pitch correction and audio synthesis using NSF-HiFiGAN neural vocoders.
语音唤醒：A lightweight, open-source, and intelligent wake word detection engine. Train custom, high-accuracy models with minimal effort.
TrendRadar
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
A production-ready RAG (Retrieval Augmented Generation) system for chatting with your documents
综合语音项目 Speech Toolkit for bahasa Malaysia, https://malaya-speech.readthedocs.io/
Mamba Voice Cloning
论文主页生成：Human-Agent Collaborative Paper-to-Page Crafting
巨人网络：IPA-based Dialect TTS
巨人网络歌声转换：YingMusic-SVC.
No description provided.
Minimal reproduction of OneRec
Jointly perform acoustic feedback cancellation and speaker extraction.
Joint Acoustic Echo Cancellation and Noise Suppression