Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC…

vits chinese, tts chinese, tts mandarin 史上训练最简单，音质最好的语音合成系统

📦 快速转化「中文数字」和「阿拉伯数字」～ (最新特性：分数，日期、温度等转化）

中文汉语拼音辞典，汉字拼音字典，词典，成语词典，常用字、多音字字典数据库

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translatio…

😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

Taming Stable Diffusion for Lip Sync!

Text Normalization & Inverse Text Normalization

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Running the F5-TTS by ONNX Runtime

SummerTTS 是一个基于C++的独立编译的中文和英文语音合成项目，可以本地运行不需要网络，而且没有额外的依赖，一键编译完成即可用于中文和英文的语音合成。SummerTTS is a standalone Chinese and English speech synthesis(TTS) project that has almost no dependency and could be…

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

HunyuanVideo: A Systematic Framework For Large Video Generation Model

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

Official repository for LTX-Video

GLM-4-Voice | 端到端中英语音对话模型

zero-shot voice conversion & singing voice conversion, with real-time support

A curated list of awesome voice conversion, projects and communities.

Let your Claude able to think

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

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

Universal Tensor Operations in Einstein-Inspired Notation for Python.

Faster Whisper transcription with CTranslate2

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

结巴中文分词