iqiyi/FASPell

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1223 stars · 212 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

FASPell is a Python-based Chinese spell checker based on the DAE-Decoder paradigm, published at the EMNLP 2019 W-NUT workshop. It detects and corrects substitution errors in both simplified and traditional Chinese texts, including human essays and OCR output.

Use cases

• detect and correct Chinese spelling errors in text
• spell check simplified and traditional Chinese essays
• fix OCR errors in Chinese documents
• replicate the FASPell EMNLP 2019 paper experiments
• evaluate Chinese spell checking on SIGHAN benchmarks
• build a Chinese text proofreading pipeline

When to choose

• you need state-of-the-art (2019-era) Chinese spell checking with published benchmarks
• you work with both simplified and traditional Chinese text
• you need to correct OCR output for Chinese documents
• you want a research-backed CSC model with code and data included

When to avoid

• you need a maintained production library with recent updates or modern framework support
• you need spell checking for languages other than Chinese
• you cannot use TensorFlow 1.x or Python 3.6-era dependencies
• you need to handle insertion/deletion errors, which are out of scope

Facets

library · maturity maintenance

nlp machine-learning deep-learning machine-learning artificial-intelligence python chinese-spell-check spell-correction ocr-post-correction simplified-chinese traditional-chinese dae-decoder tensorflow research-paper natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="iqiyi/FASPell")