Kur alternatives for AI agents.

speech to text benchmark framework

High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！

Open source, local, and self-hosted highly optimized language inference server supporting ASR/STT, TTS, and LLM across WebRTC, REST, and WS

基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。

基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

Optimized Whisper models for streaming and on-device use

On-device Speech-to-Intent engine powered by deep learning

A SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and both speech and singing ASR. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects. FireRedPunc supports zh and en.

On-device streaming speech-to-text engine powered by deep learning

人工智能学习资料超全整理，包含机器学习基础ML、深度学习基础DL、计算机视觉CV、自然语言处理NLP、推荐系统、语音识别、图神经网路、算法工程师面试题

The hub for audio AI research: papers, open models, benchmarks & datasets across audio LLMs, speech recognition, TTS, music & audio generation.

A talking LLM that runs on your own computer without needing the internet.

📦 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）