chenkui164/FastASR
这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来，数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小时)， 所以识别效果也很好，可以媲美许多商用的ASR软件。
This project offers robust speech-to-text conversion for Mandarin Chinese and some English audio, transforming spoken words into accurate text. It's designed for situations where you need to quickly process audio on devices like embedded systems or single-board computers, without relying on powerful GPUs. This is ideal for developers and engineers building applications that require efficient local voice transcription.
547 stars. No commits in the last 6 months.
Use this if you need to integrate fast, accurate Chinese and English speech recognition directly into your applications, especially on resource-constrained hardware like Raspberry Pi.
Not ideal if you need a pre-built, end-user application for speech-to-text, or if your primary requirement is transcription for languages other than Chinese and basic English.
Stars
547
Forks
81
Language
C
License
Apache-2.0
Category
Last pushed
Mar 19, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/chenkui164/FastASR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with...
k2-fsa/sherpa
Speech-to-text server framework with next-gen Kaldi
Picovoice/cheetah
On-device streaming speech-to-text engine powered by deep learning
yeyupiaoling/YeAudio
Python的音频工具
zaigie/FunSpeech
开箱即用的本地私有化部署语音服务，快速搭建FunASR与CosyVoice2/3后端