Lists (1)
Stars
[ICML 2025] PyTorch Implementation of "OmniAudio: Generating Spatial Audio from 360-Degree Video"
MeshRIR: Dataset of room impulse responses on meshed grid points
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
code repo for LoCoNet: Long-Short Context Network for Active Speaker Detection
Hearing Anything Anywhere Code Release
Impulse response generation based on state-of-the-art geometric sound propagation engine.
A multizone sound field control method to synthesize a desired amplitude (or magnitude) distributions over a target region with multiple loudspeakers
Speaker embedding (d-vector) trained with GE2E loss
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
In defence of metric learning for speaker recognition
PyTorch implementation for Histogram Loss
Graph Neural Network Library for PyTorch
ACM MM 2021: 'Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection'
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)
Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection (ECCV 2022)
PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
Official code for "Continual Prompt Tuning for Dialog State Tracking" (ACL 2022).
Continual Learning for Task-Oriented Dialogue Systems
Avalanche: an End-to-End Library for Continual Learning based on PyTorch.
Tracking the progress in SLU (resources, code, and new frontiers etc.)
Python wrapper for Stanford CoreNLP's SUTime
CogDL: A Comprehensive Library for Graph Deep Learning (WWW 2023)