Mingqi Jiang

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

A pitch detection model trained to be robust against noise and reverberation environments.

A Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"

语音方向实验室/公司/资源/实习等，欢迎推荐或自荐（排名不分先后）

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

personal github page

Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.

无需服务器，一键部署，快速使用自建节点分享URL进行订阅转换，提供灵活的自定义选项，支持SingBox/Clash/V2Ray/Xray

No description.

Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice

It is some useful script for personal daily work.

No description.

No description.

沪语（上海话）ASR（语音识别）模型

一些不错的中文podcasts

No description.

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor