yeyupiaoling/MASR
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。
This project offers an automatic speech recognition (ASR) framework that converts spoken audio into text. It accepts audio recordings in various languages, including Mandarin, Cantonese, English, and Uyghur, and outputs the corresponding transcribed text. This tool is for developers or researchers who need to integrate high-quality speech-to-text capabilities into their applications or analyze audio data.
724 stars. Available on PyPI.
Use this if you need a flexible, high-performance speech-to-text solution that supports multiple languages and can be customized with various models and decoding strategies for both real-time and offline processing.
Not ideal if you're an end-user looking for a ready-to-use speech transcription app without any development or technical setup.
Stars
724
Forks
114
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 17, 2025
Commits (30d)
0
Dependencies
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yeyupiaoling/MASR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
shivammehta25/Neural-HMM
Neural HMMs are all you need (for high-quality attention-free TTS)