Jun Xue's starred repositories
PyTorch-VAE
A Collection of Variational Autoencoders (VAE) in PyTorch.
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
STgram-MFN
A spectro-temporal fusion feature, STgram, with MobileFaceNet For more stable Anomalous Sound Detection
emotion2vec
[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation
FSD-Dataset
This repository presents a subset of our proposed FSD dataset for song deepfake detection.
SpeechFormer2
SpeechFormer++ in PyTorch
SSL_Anti-spoofing
This repository includes the code to reproduce our paper "Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation".
w2v2-how-to
How to use our public wav2vec2 dimensional emotion model
RawBoost-antispoofing
This repository includes the code to reproduce our paper "RawBoost: A Raw Data Boosting and Augmentation Method applied to Automatic Speaker Verification Anti-Spoofing".
chatgpt-on-wechat
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择GPT3.5/GPT-4o/GPT4.0/ Claude/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Claude/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
Self-Distillation
Improve a Model's accuracy by distilling knowledge to the earlier layers of the model. Improves accuracy and performance of lightweight DNN models
project-NN-Pytorch-scripts
see README
leaf-pytorch
PyTorch implementation of the LEAF audio frontend