Official code of ICML 2025 paper "NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction"

LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey | Awesome Human-Agent Collaboration | Human-AI Collaboration

Code for our NeurIPS 2022 paper

open-source coding LLM for software engineering tasks

Kimi K2 is the large language model series developed by Moonshot AI team

A resource to create a multi domain Dialog Act Tagger for conversational agents using publicly available data

Vogent Turn: fast, open-source turn-detection for Voice AI applications

We Speech Toolkit, LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction

Text Normalization & Inverse Text Normalization

Evaluating the Moral Beliefs Encoded in LLMs

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI

Simplifying reinforcement learning for complex game environments

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

The Gridspace-Stanford Harper Valley speech dataset. Created in support of CS224S.

This is an evolving repo for the paper “From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Models ”A comprehensive survey of Full-Duplex Spoken Language Models (FD-SL…

(Realtime) Temporal Convolutions in PyTorch

portion, a Python library providing data structure and operations for intervals.

Official Implementation of NAACL 2025 Paper: Behavior-SD: Behaviorally Aware Spoken Dialogue Generation with Large Language Models

Official PyTorch implementation of EMOVA in CVPR 2025 (https://arxiv.org/abs/2409.18042)

Open-Source Turn-Taking Detection Model and Dataset for Full-Duplex Spoken Dialogue Systems

OSUM & OSUM-EChat, open speech understanding model and empathetic spoken chatbot based on it, open-sourced by ASLP@NPU.

Code for the paper "Modelling Turn-taking in Multispeaker Parties for Realistic Data Simulation"

FLM-Audio is a audio-language subversion of RoboEgo/FLM-Ego -- an omnimodal model with native full duplexity.

Python toolkit for speech processing