jpuigcerver/Laia
Laia: A deep learning toolkit for HTR based on Torch
This toolkit helps researchers and archivists automatically convert scanned handwritten text images into digital text. You provide images of handwritten documents and corresponding transcripts, and it generates a trained model that can transcribe new handwritten images into plain text. This is ideal for anyone working with historical documents, archives, or large collections of handwritten material that needs to be digitized and made searchable.
151 stars. No commits in the last 6 months.
Use this if you need to build a system to automatically transcribe large volumes of handwritten documents for digitization and text-based analysis.
Not ideal if you need a tool for general document OCR (optical character recognition) that handles typed text, or if you prefer a solution that runs without a GPU.
Stars
151
Forks
56
Language
Shell
License
MIT
Category
Last pushed
Jun 25, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jpuigcerver/Laia"
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