TTSAudioNormalizer is a specialized tool for TTS data production, featuring descriptive statistical analysis of audio loudness and loudness normalization operations.

Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组

Official implementation of the NeurIPS 24 paper of statistical flow matching (SFM) for discrete generation.

Unsupervised text tokenizer for Neural Network-based text generation.

Official inference repo for FLUX.1 models

《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新，English version ongoing

ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations

A Survey of Spoken Dialogue Models (60 pages)

Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch

PyTorch implementation of Soft-DTW: a Differentiable Loss Function for Time-Series in CUDA

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

first base model for full-duplex conversational audio

🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.

A 6-million Audio-Caption Paired Dataset Built with a LLMs and ALMs-based Automatic Pipeline

🚀 Next Generation AI One-Stop Internationalization Solution. 🚀 下一代 AI 一站式 B/C 端解决方案，支持 OpenAI，Midjourney，Claude，讯飞星火，Stable Diffusion，DALL·E，ChatGLM，通义千问，腾讯混元，360 智脑，百川 AI，火山方舟，新必应，Gemini，Moonshot …

Robust Speech Recognition via Large-Scale Weak Supervision

SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

GLM-4-Voice | 端到端中英语音对话模型

Open-Sora: Democratizing Efficient Video Production for All

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

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

Implementation of Autoregressive Diffusion in Pytorch

Foundational Models for State-of-the-Art Speech and Text Translation

Next-Token Prediction is All You Need

Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

Official github page of Oceanship Dataset

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on