Yihui Fu's Projects
Music Source Separation; Train & Eval & Inference piplines and pretrained models we used for 2021 ISMIR MDX Challenge.
A workspace for single/multi-channel speech recognition & enhancement & separation.
Python 爬取B站UP主的所有视频链接及详细信息
Pre-Training with Whole Word Masking for Chinese BERT(中文BERT-wwm系列模型)
An unofficial implementation of DeepVQE proposed by Microsoft Corp.
Config files for my GitHub profile.
Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.
G722格式音频编解码
G722 and G722.1 file encoders for FreeSWITCH
Tools for Speech Enhancement integrated with Kaldi
Speech, Language, Audio, Music Processing with Large Language Model
Awesome speech/audio LLMs, representation learning, and codec models
泡面哥汤达人的前世今生,从默默无闻到人人喊打【截止到2019年12月9日】
Unofficial Pytorch Lightning Implementation of "Towards Robust Speech Super-Resolution"
Uformer: A Unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation
Robust Speech Recognition via Large-Scale Weak Supervision
Command-line program to download videos from YouTube.com and other video sites