# iqiyi/FASPell

2019-SOTA简繁中文拼写检查工具：FASPell Chinese Spell Checker (Chinese Spell Check / 中文拼写检错 / 中文拼写纠错 / 中文拼写检查)

Repository: https://github.com/iqiyi/FASPell
Canonical: https://ross.abutalabs.com/products/faspell
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2022-09-03T07:33:09+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2533, "days_push": 1460, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1223, forks 212 (observed 2026-08-28T04:04:02.648537+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, deep-learning
- domain: machine-learning, artificial-intelligence
- platform: python
- tags: chinese-spell-check, spell-correction, ocr-post-correction, simplified-chinese, traditional-chinese, dae-decoder, tensorflow, research-paper, natural-language-processing

## Member repositories
- iqiyi/FASPell (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:02.648537+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:15:33.263483+00:00, confidence not recorded.
  - readme: https://github.com/iqiyi/FASPell (fetched 2026-08-28T04:04:02.648537+00:00, sha d25818514d88)
- Data as of 2026-08-30T08:39:29.467469+00:00.