Punctuation restoration and spell correction experiments.
Extremely easy to use sequence to sequence library with attention, for text to text conversion tasks.
文本纠错工具包(Text Correct, CSC), 支持中文文本纠错(拼写纠错/标点符号纠错)(CSC, Chinese Spelling Correct / Check; Punct), CSC支持各领域数据的中文文本纠错(包括古文), 模型在大规模、各领域的、现代/当代语料上训练而得, 泛化性强.重点是错别字检测纠正.
Automatically punctuate lecture transcripts obtained from YouTube.
A simple streamlit based webapp to process text and correct punctuation built using "fullstop-punctuation-multilang-large" Model from Huggingface Transformers 🤗.
Want to type an Em Dash—now you can. Just type "--".
解决OCR或LLM（比如Claude）中文输出时偶尔冒出的英文标点https://p.gantrol.com
Seq2Seq model that restores punctuation on English input text.
A tool for analysing text data in Django backend
This repository contains a Python script that compiles a set of the most common puncturation and comma-setting rules in the Danish language. Achieving perfect comma placement in Danish can be notoriously challenging due to competing conventions. With this script, you can process your input text to ensure correct comma placement. Enjoy!
Indexing and Retrieval Models
Punctuation restoration using transformer on languages: RU, EN, FR, DE
Add a description, image, and links to the punctuation-correction topic page so that developers can more easily learn about it.
To associate your repository with the punctuation-correction topic, visit your repo's landing page and select "manage topics."