binzhouchn/masr
中文语音识别系列，读者可以借助它快速训练属于自己的中文语音识别模型，或直接使用预训练模型测试效果。
This project helps you turn spoken Chinese into written text. You provide Chinese audio files, and it delivers accurate Chinese text transcriptions. It's designed for researchers, developers, or anyone needing to quickly build or use a customized speech-to-text system for Chinese audio.
285 stars. No commits in the last 6 months.
Use this if you need to transcribe spoken Chinese audio into text, whether through a ready-to-use solution or by training a specialized model for your unique audio data.
Not ideal if you need a production-scale, enterprise-grade speech recognition system with extremely high accuracy on diverse, uncontrolled audio out-of-the-box, as it requires further customization for such scenarios.
Stars
285
Forks
43
Language
Python
License
—
Category
Last pushed
Mar 23, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/binzhouchn/masr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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。
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