TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Trans Router

[arXiv 2024] Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]

✨✨VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Implementation of TTS model based on NVIDIA P-Flow TTS Paper

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

Everything about the SmolLM & SmolLM2 family of models

Official repository for LTX-Video

NanoGPT (124M) in 3.4 minutes

proof of concept conversation orchestrator with a speech-language model

Joint speech-language model - respond directly to audio!

Unified Speech Language Model for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"(ICLR 2024)

A Survey of Spoken Dialogue Models (60 pages)

LSLM implements full duplex modeling in interactive speech language models, based on research by Ma et al. (2024). This project advances human-computer interaction through real-time spoken dialogue…

Let's finetune video generation models!

Ultra-low bitrate neural audio codec (0.31~1.40 kbps) with a better semantic in the latent space.

Interface for OuteTTS models.

first base model for full-duplex conversational audio

Models and code for RepCodec: A Speech Representation Codec for Speech Tokenization

An Open-source Streaming High-fidelity Neural Audio Codec

Realtime Video and Audio Streaming with WebRTC and Gradio

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

Minimalistic large language model 3D-parallelism training

GLM-4-Voice | 端到端中英语音对话模型

Fast and accurate automatic speech recognition (ASR) for edge devices

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.