Julio Hsu
juliohsu
Researcher at @moises-ai | Member of @SmallDoges & @nnAudio
Languages
Top Repositories
Tutorial - How to implement Object Detection by YOLO?
University Project of Networking - Connection FTCP
A study of Atlantic people on their dataset, with R script and Linear Regression model prediction statistics
Repositories
56No description provided.
No description provided.
No description provided.
No description provided.
High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！
No description provided.
OpenSource Project - UFCG LLM25.2
No description provided.
No description provided.
Small DIalogue Language Model (SDLM)
Tutorial - How to implement Object Detection by YOLO?
A method that directly addresses the modality gap by aligning speech token with the corresponding text transcription during the tokenization stage.
No description provided.
Audio Processing Studies
LLM Studies
Variable Q-Transform
Audio processing by using pytorch 1D convolution network
Accurate and general beat tracker
Projeto de Redes de Computadores 2024.2
University Project of Networking - Connection FTCP
No description provided.
Speech to Text Neural Network
Multitrack Web Audio editor and player with canvas waveform preview. Set cues, fades and shift multiple tracks in time. Record audio tracks or provide audio annotations. Export your mix to AudioBuffer or WAV! Add effects from Tone.js. Project inspired by Audacity.
Neural Audio Encoder
State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.
Config files for my GitHub profile.
A study of Atlantic people on their dataset, with R script and Linear Regression model prediction statistics
No description provided.
Skin Cancer Convolutional Model
A low-bitrate single-codebook 16 kHz speech codec based on focal modulation