57 projects
tokenmaxxing
Menu bar app showing your live Claude Code session and weekly usage as a colored progress bar.
expletives
Curated profanity lists with provenance, categorisation, and simple matching helpers.
unfairseq
Un-fairseq: UnFormers (Universal Transformers) — config-driven enc-dec chassis covering NLLB/mBART/Marian/mT5/UL2/t5gemma/TranslateGemma/Qwen/Gemma, plus Matryoshka encoder, Garg 2019 supervised attention, PyTorch IBM Models 1/2/HMM/4, Brown+k-means clustering, and portable char/byte alignment.
bespoke
Bespoke trading strategy library — backtest, compare, and build custom strategies
pywsd-datasets
Unified Word Sense Disambiguation benchmark datasets, normalized to modern wn lexicon sense IDs (oewn:2024 and omw:*).
pywsd
Python Implementations of Word Sense Disambiguation (WSD) technologies.
charguana
A character vomiting library — Unicode character sets for CJK, Thai, Vietnamese, and Perl uniprops.
lazyme
Lazy python recipes
lightyear
Unified MT evaluation toolbox: BLEU, CHRF, TER, BERTScore, SentenceBERTScore, COMET, CometKiwi, MetricX-23/24, PreCOMET, Sentinel-src — built on transformers + torch + sacrebleu.
nltk
Natural Language Toolkit
sacremoses
SacreMoses
lazyface
lazyface
whyclick
Cos I don't like to click
skformer
skformer
stash-data
colorless
Colorless green ideas sleep furiously
prism-mt
prism-mt
uchu
Sane interface to cloud services.
spirit-guess
sacrefilter
necessity
Bear necessity
soundsgood
Cos I don't think https://docs.python.org/3/tutorial/modules.html#packages is at all sound...
mindset
Mindset
aomame
Aomame
rubyslippers
warppipe
moulton
translate-hub
Translate Hub
nltkdata
NLTK Data
kuddelmuddel
Translation Memory Munger
herecomes
Here comes a new challenger
yubin
Japanese Address Munger
farfetcher
thallium
Lazy python recipes with batteries
evilunicorn
Evil Unicorn
subtitles
Python WSD
soyuz
NLTK API with SpaCy models.
gopeng
Pythonic RapidAPI calls
dopplershift
Pythonic SQL for mere mortals.
ruth
Ruth
onigiri
Unofficial RIT Translate
xgbert
sherbert
sherbert
sherbert
hinzkunz
Hinz und Kunz
gudetama
Lazy python recipes with batteries
takopachi
Takopachi
kintsugi
tsundoku
Coursework for Text Processing using Machine Learning at NUS-ISS
tokfu
Tokfu
komorebi
Text data plumbing
toktok
Toktok tokenizer
mitochondria
tinkle
Data Simplified
tofukatsu
Tokenization Factory.
earthy
UNKNOWN
carjack
UNKNOWN
rubberduck
Yet another DuckDuckGo Python API
