metasequoiaime/chinese-ime-lm
Library
Can I trust it?
Worth a closer look before you use it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 2 days ago.
Licence Check
GPL-3.0: free to use. If you distribute software that includes it, you must publish your code under the same licence.
Quick checks from public data. They help, but they are no guarantee.
What it is
Language-model engineering for Chinese input methods: corpus cleaning, KenLM n-gram statistics, a character-level Transformer that reranks pinyin decoding candidates, and an evaluation set of word-level and sentence-level cases. Weights are published on Hugging Face under…
Who it's for
Developers building Chinese pinyin input methods or researching language models for candidate ranking
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up metasequoiaime/chinese-ime-lm in my project. Follow its README: https://github.com/metasequoiaime/chinese-ime-lm. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
18,995 GitHub repos watched and ranked every hour. Figures as of 22 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/metasequoiaime/chinese-ime-lm?ref=badge)Similar repos
- 0c-biggo/0c-ime
An offline Zhuyin (Bopomofo) input method for Traditional Chinese that uses an on-device Transformer to rerank candidates based on preceding text, with a statistical fallback. Shells are provided for
- rootSunc/CNEquity
A local data lake for Chinese A-share market data covering quotes, fundamentals, futures, capital flows, corporate events, indices, and macro indicators. It supports incremental collection, resumable
- HazyResearch/ncm
Research code for Next-Concept Modeling, a two-stage framework for parallel text generation. A multiscale residual VQ tokenizer maps sequences to hierarchical discrete codes, and a transformer predict
- qlabs-eng/noise
A pretraining speedrun for language model learning algorithms that never run a backward pass. It fixes a 37.7M-parameter transformer, a 10M-token FineWeb training set and a validation cross-entropy sc
- larashero3-dotcom/lieflat-less-ai-tone
A Chinese-language skill for removing so-called AI tone from writing. It flags specific sentence and paragraph patterns, such as contrastive structures, colons, dashes and zero-referent paragraph open
- inclusionAI/Ming-3.0-tts
Multilingual text-to-speech models (0.5b dense and tiny MoE) with voice cloning, voice design, built-in voices, natural-language style instructions and inline paralinguistic tags. Includes inference c