pypi.org "multilingual" keyword
Top 6.9% on pypi.org
192 versions - Latest release: almost 2 years ago - 4 dependent repositories - 510 downloads last month - 305 stars on GitHub - 1 maintainer
text2text 1.9.5
Text2Text Language Modeling Toolkit192 versions - Latest release: almost 2 years ago - 4 dependent repositories - 510 downloads last month - 305 stars on GitHub - 1 maintainer
Top 1.8% on pypi.org
15 versions - Latest release: about 2 months ago - 4 dependent packages - 506 dependent repositories - 7.7 thousand downloads last month - 57 stars on GitHub - 2 maintainers
mathparse 0.2.9 π°
mathparse is a library for solving mathematical equations contained in strings15 versions - Latest release: about 2 months ago - 4 dependent packages - 506 dependent repositories - 7.7 thousand downloads last month - 57 stars on GitHub - 2 maintainers
ovos-date-parser 0.29.0 π°
OpenVoiceOS's multilingual date and time parsing and formatting library117 versions - Latest release: 3 months ago - 38.3 thousand downloads last month - 0 stars on GitHub - 1 maintainer
piper-plus 2.0.2 π°
A fast, high-quality neural text-to-speech system supporting 8 languages (ja/en/zh/ko/es/fr/pt/sv...7 versions - Latest release: 7 days ago - 2.53 thousand downloads last month - 238 stars on GitHub - 1 maintainer
piper-plus-g2p 0.3.1 π°
Multilingual G2P (Grapheme-to-Phoneme) for TTS β eSpeak-ng free, MIT licensed3 versions - Latest release: 7 days ago - 407 downloads last month - 238 stars on GitHub - 1 maintainer
piper-tts-plus 20250711.64548 π°
This package has been renamed to piper-plus. Install piper-plus instead.53 versions - Latest release: over 1 year ago - 1.17 thousand downloads last month - 238 stars on GitHub - 1 maintainer
livekit-plugins-upliftai 1.8.8
Agent Framework plugin for speech synthesis with the Uplift AI.80 versions - Latest release: 8 days ago - 1.97 thousand downloads last month - 14,860 stars on GitHub - 1 maintainer
livekit-plugins-smallestai 1.8.8
Agent Framework plugin for speech synthesis and recognition with Smallest AI.77 versions - Latest release: 8 days ago - 11.9 thousand downloads last month - 14,860 stars on GitHub - 1 maintainer
laurus 0.13.2 π°
Python bindings for the Laurus search library13 versions - Latest release: about 1 month ago - 734 downloads last month - 28 stars on GitHub - 1 maintainer
cyg 0.0.1b1.post4
A Python library to query the Cygnet multilingual wordnet database5 versions - Latest release: about 1 month ago - 0 stars on GitHub - 1 maintainer
altamt 1.1
ALTAMT: Advanced Lightweight Translation AI Model Transformer - multilingual Kinyarwanda/English/...2 versions - Latest release: 2 months ago - 1 maintainer
chronologia 0.2.9
General-purpose calendrical and chronological core: unbounded datetime-compatible dates, half-ope...129 versions - Latest release: 2 months ago - 34.4 thousand downloads last month - 2 stars on GitHub - 1 maintainer
fast-universal-sentence-encoder 0.2.1
Fast, dependency-light Google USE multilingual v3 sentence embeddings (pure numpy, no C++ deps)3 versions - Latest release: about 2 months ago - 179 downloads last month - 1 stars on GitHub - 1 maintainer
dodduytts 0.3.0
DoDuyTTS: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models1 version - Latest release: 2 months ago - 0 stars on GitHub - 1 maintainer
custovox-sentiment 1.0.3
Multilingual customer sentiment analysis MCP server. EN/FR/DE/ES/PT-BR native models. By custovox.ai4 versions - Latest release: 4 days ago - 21 downloads last month - 0 stars on GitHub - 1 maintainer
ovos-tts-plugin-omnivoice 0.0.2a1 π°
OmniVoice massively-multilingual zero-shot TTS plugin for OpenVoiceOS1 version - Latest release: 3 months ago - 22 downloads last month - 1 stars on GitHub - 1 maintainer
quanfire-multilingual-embedding 0.6.0
Production-ready multilingual NLP and embedding framework3 versions - Latest release: 2 months ago - 0 stars on GitHub - 1 maintainer
glossobench 1.3.0
Open-source, judge-agnostic LLM benchmark for any language β natural or AI-developed. Public data...7 versions - Latest release: 3 months ago - 40 downloads last month - 2 stars on GitHub - 1 maintainer
speaker-helper 0.8.0
Speaker Helper β speech synthesis that runs in your process: say a sentence, stream a reply, or n...3 versions - Latest release: 4 days ago - 20 downloads last month - 0 stars on GitHub - 1 maintainer
ms3p-sushima-tokenizer 3.0.0
MS3P Sushima byte-level BPE tokenizer engine with multilingual synthetic corpus generation.1 version - Latest release: 3 months ago - 22 downloads last month - 0 stars on GitHub - 1 maintainer
Top 7.4% on pypi.org
148 versions - Latest release: about 1 month ago - 5 dependent packages - 1 dependent repositories - 273 thousand downloads last month - 20,755 stars on GitHub - 1 maintainer
funasr 1.4.16
OpenAI-compatible speech recognition toolkit with WebSocket streaming, vLLM acceleration, and lla...148 versions - Latest release: about 1 month ago - 5 dependent packages - 1 dependent repositories - 273 thousand downloads last month - 20,755 stars on GitHub - 1 maintainer
shog-ai 0.1.0
Streaming dataset engineering library for multilingual AI and foundation model pretraining.1 version - Latest release: 3 months ago - 0 stars on GitHub - 1 maintainer
multilingual-dev-rag 0.2.1
Local-first multilingual RAG for code and technical docs. In-process hybrid retrieval (vector + f...5 versions - Latest release: 3 months ago - 34 downloads last month - 0 stars on GitHub - 1 maintainer
oruk-bench 0.1.1
Public tooling for the Oruk speech-emotion benchmark: data loading, scoring, model adapters, and ...1 version - Latest release: 3 months ago - 13 downloads last month - 0 stars on GitHub - 1 maintainer
verbatimeter 0.1.3
Deterministically verify how grounded an AI-generated text is in its source β highlight verbatim ...6 versions - Latest release: 3 months ago - 55 downloads last month - 5 stars on GitHub - 1 maintainer
entirius-django-faq 2.1.0
FAQ module for Entirius: translated, channel-scoped questions and answers linked to products, cat...2 versions - Latest release: 11 days ago - 94 downloads last month - 0 stars on GitHub - 1 maintainer
linguin-api 0.1.0
Official Python client for the Linguin API: multilingual dictionary lookups, reverse dictionary, ...1 version - Latest release: 4 months ago - 17 downloads last month - 0 stars on GitHub - 1 maintainer
lindera-python-cc-cedict 2.2.0 π°
Python binding for Lindera with CC-CEDICT Chinese dictionary11 versions - Latest release: 8 months ago - 93 downloads last month - 695 stars on GitHub - 1 maintainer
lindera-python-unidic 2.2.0 π°
Python binding for Lindera with UniDic dictionary11 versions - Latest release: 8 months ago - 50 downloads last month - 695 stars on GitHub - 1 maintainer
lindera-python-jieba 2.2.0 π°
Python binding for Lindera with Jieba Chinese dictionary1 version - Latest release: 7 months ago - 19 downloads last month - 695 stars on GitHub - 1 maintainer
lindera-python-ipadic 2.2.0 π°
Python binding for Lindera with IPADIC dictionary11 versions - Latest release: 8 months ago - 318 downloads last month - 695 stars on GitHub - 1 maintainer
lindera-python-ko-dic 2.2.0 π°
Python binding for Lindera with ko-dic Korean dictionary11 versions - Latest release: 8 months ago - 37 downloads last month - 695 stars on GitHub - 1 maintainer
lindera-python-cjk 2.2.0 π°
Python binding for Lindera with CJK dictionaries (IPADIC, ko-dic, CC-CEDICT)11 versions - Latest release: 8 months ago - 55 downloads last month - 695 stars on GitHub - 1 maintainer
lindera-python 6.0.0 π°
Renamed to 'lindera'. This stub only depends on the new name.27 versions - Latest release: 30 days ago - 1.47 thousand downloads last month - 695 stars on GitHub - 1 maintainer
laya 0.4.12
Fast, non-autoregressive System 1 decision engine with calibrated probabilities50 versions - Latest release: 4 days ago - 272 thousand downloads last month - 33,515 stars on GitHub - 1 maintainer
asia-fertility 0.4.0
Tokenizer fertility, cost, and multi-turn context-budget analyzer for low-resource Asian languages.6 versions - Latest release: 4 months ago - 53 downloads last month - 2 stars on GitHub - 1 maintainer
yasbd-auxlang 0.2.0
Constructed language support for yasbd-lib β Esperanto, Interlingua, and more.3 versions - Latest release: about 2 months ago - 23 downloads last month - 1 stars on GitHub - 1 maintainer
yasbd-union 0.2.0
Experimental multilingual aggregate for yasbd-lib β best-effort sentence splitting over all insta...2 versions - Latest release: about 2 months ago - 24 downloads last month - 2 stars on GitHub - 1 maintainer
ne-embed 1.0.0
Multilingual text embeddings for Northeast Indian languages1 version - Latest release: 4 months ago - 17 downloads last month - 0 stars on GitHub - 1 maintainer
readsight 1.0.5
Multilingual readability library for Python β 86 languages, 17 formulas, TeX-based syllable count...6 versions - Latest release: 3 months ago - 46 downloads last month - 26 stars on GitHub - 1 maintainer
decima-ai 2.3.0
Decima β a small, calibrated, multilingual decision model: situation + question + your options β ...2 versions - Latest release: 5 days ago - 0 downloads last month - 1 stars on GitHub - 1 maintainer
synthreat 0.1.1
Reproducible synthetic multilingual threat-intelligence datasets (EN/RU/ZH/DE) with risk labels a...2 versions - Latest release: 3 months ago - 23 downloads last month - 1 stars on GitHub - 1 maintainer
universal-render 0.1.0
Universal complex-script text rendering for Matplotlib and Seaborn using Qt/HarfBuzz shaping.1 version - Latest release: 3 months ago - 136 downloads last month - 0 stars on GitHub - 1 maintainer
osintlens 0.1.0
Multilingual OSINT analysis in a single call: language detection, IOC extraction, entity recognit...1 version - Latest release: 3 months ago - 1 stars on GitHub - 1 maintainer
dubbed-video-downloader 0.2.0
Download YouTube videos or audio with a selected dubbed audio track.1 version - Latest release: 4 months ago - 25 downloads last month - 8 stars on GitHub - 1 maintainer
chronoparse 0.1.0
Universal datetime parser supporting all real-world date and time formats across all countries an...1 version - Latest release: 4 months ago - 1 maintainer
yasbd-xx 0.1.0
Experimental multilingual aggregate for yasbd-lib β best-effort sentence splitting over all insta...1 version - Latest release: 4 months ago - 1 stars on GitHub - 1 maintainer
polystring 1.0.0
Span-level language detection for mixed-language text2 versions - Latest release: about 2 months ago - 128 downloads last month - 0 stars on GitHub - 1 maintainer
privyscope 0.1.6
privyscope β multilingual PII detection & masking engine (ONNX, BIOES + Viterbi). Install a langu...5 versions - Latest release: 9 days ago - 35 downloads last month - 1 stars on GitHub - 1 maintainer
simple-localize 1.0.1
A simple, thread-safe Python module for easy localization (multilingual support)2 versions - Latest release: 4 months ago - 59 downloads last month - 0 stars on GitHub - 1 maintainer
mtg-guards 0.1.0
Morphological Type Guards β a JSON Schema extension for multilingual tool-call arguments1 version - Latest release: 5 months ago - 15 downloads last month - 0 stars on GitHub - 1 maintainer
disinfolib 1.0.0
Streaming library for disinformation detection in multilingual text streams1 version - Latest release: 5 months ago - 8 downloads last month - 0 stars on GitHub - 1 maintainer
hyper-gliner 0.1.3
Torch-only inference for grounded infon extraction: paragraph in -> typed, grounded, polarity-awa...4 versions - Latest release: 4 months ago - 1 maintainer
obsei 1.1.1
Open source, privacy-first Voice of Customer analytics. A self-hosted alternative to Enterpret an...24 versions - Latest release: 6 days ago - 3 dependent repositories - 527 downloads last month - 1,439 stars on GitHub - 1 maintainer
entiscope 0.1.0
entiscope β multilingual PII detection & masking engine (ONNX, BIOES + Viterbi). Install a langua...1 version - Latest release: 4 months ago - 281 downloads last month - 1 stars on GitHub - 1 maintainer
cohere-ledgerproof 0.1.0
LedgerProof adapter for the Cohere Python SDK. Side-channel transparency receipts for EU AI Act A...1 version - Latest release: 5 months ago - 116 downloads last month - 1 maintainer
sarvam-cli 0.1.0
Developer-first command-line interface for Sarvam AI.1 version - Latest release: 5 months ago - 27 downloads last month - 1 maintainer
ydata-profiling-multilingual 1.1.1
forked from ydataai/ydata-profiling and modify the code to support international multilingual fun...9 versions - Latest release: 8 months ago - 599 downloads last month - 2 stars on GitHub - 1 maintainer
sentimentai-py 2.0.0
Simple, tunable sentiment analysis from sentence embeddings β TensorFlow-free. Python sibling of ...2 versions - Latest release: 5 months ago - 20 downloads last month - 55 stars on GitHub - 1 maintainer
gf-wordnet 0.0.17
An API to the GF WordNet.17 versions - Latest release: over 2 years ago - 40 downloads last month - 33 stars on GitHub - 1 maintainer
invovate 0.1.2
Official Python SDK for the free, no-signup Invovate invoice API β generate PDF, JSON & UBL 2.1 i...3 versions - Latest release: 5 months ago - 330 downloads last month - 0 stars on GitHub - 1 maintainer
ragzero 0.1.0
Production-ready RAG with near-zero hallucination. Pluggable providers (OpenAI, Anthropic, Gemini...1 version - Latest release: 5 months ago - 8 downloads last month - 2 stars on GitHub - 1 maintainer
synthetictext 0.2.0
LLM-powered synthetic text data generation for text classification tasks, with multi-strategy gen...2 versions - Latest release: 4 months ago - 33 downloads last month - 0 stars on GitHub - 1 maintainer
infon 0.1.1
Streaming knowledge-graph reasoner with a typed query layer (multilingual SPLADE + Dempster-Shafe...2 versions - Latest release: 5 months ago - 1 maintainer
zaza-semantic-engine 3.2.0
Local-first multi-format document ingestion engine with semantic search using sentence-transforme...4 versions - Latest release: 5 months ago - 12 downloads last month - 0 stars on GitHub - 1 maintainer
integreat-cms 2026.9.1 π°
Content Management System for the Integreat App155 versions - Latest release: about 1 month ago - 2 dependent repositories - 460 downloads last month - 64 stars on GitHub - 2 maintainers
agent-tool-router 0.4.0
Pick the right tools for an agent task. Boring baseline. Open dataset.1 version - Latest release: 5 months ago - 28 downloads last month - 0 stars on GitHub - 1 maintainer
pipecat-gnani 0.5.12
Pipecat service integration for Gnani speech AI β STT & TTS for Indian languages16 versions - Latest release: 2 months ago - 486 downloads last month - 0 stars on GitHub - 1 maintainer
lattice-asr 0.1.1
Hardware-adaptive multilingual ASR library for the Lattice family. Pluggable engines (Parakeet, W...2 versions - Latest release: 5 months ago - 12 downloads last month - 0 stars on GitHub - 1 maintainer
name-variants 0.1.3
Multilingual name romanization lookup tables: Chinese, Japanese, Korean, Arabic, Vietnamese, Indi...4 versions - Latest release: 5 months ago - 41 downloads last month - 0 stars on GitHub - 1 maintainer
sarvam-tts 1.1
A Python client for Sarvam AI text-to-speech that supports multilingual Indian language synthesis.2 versions - Latest release: 5 months ago - 23 downloads last month - 0 stars on GitHub - 1 maintainer
strands-omnivoice 0.1.0 π°
OmniVoice multilingual zero-shot TTS toolkit for Strands Agents β voice cloning, voice design, an...1 version - Latest release: 5 months ago - 48 downloads last month - 2 stars on GitHub - 1 maintainer
ryokai 0.1.0
δΊθ§£ β unified semantic MT evaluation: MEANT, XMEANT, YiSi, WOLVESAAR, and SimAlign-style word alig...1 version - Latest release: 5 months ago - 48 downloads last month - 0 stars on GitHub - 1 maintainer
polyglean 0.1.1
A universal text cleaning and dataset preparation library for any language or script.2 versions - Latest release: 6 months ago - 11 downloads last month - 1 stars on GitHub - 1 maintainer
polymath-ai 0.1.0
Zer0pa Polymath AI β on-device LLM training research infrastructure for multilingual experiments.1 version - Latest release: 6 months ago - 3 downloads last month - 1 stars on GitHub - 1 maintainer
livekit-plugins-gnani 1.6.9
LiveKit Agents plugin for Gnani Vachana speech AI β STT & TTS for Indian languages29 versions - Latest release: 3 months ago - 2.61 thousand downloads last month - 1 stars on GitHub - 1 maintainer
tenderness 0.3.0
Text rendering library with pipelines for synthetic document generation4 versions - Latest release: 3 months ago - 29 downloads last month - 15 stars on GitHub - 1 maintainer
mothertoken 0.1.1
Benchmarking tool for tokenizer efficiency across languages and models4 versions - Latest release: 4 months ago - 21 downloads last month - 5 stars on GitHub - 1 maintainer
pruneforge 0.1.4
A Hierarchical Pruning Architecture for On-Device Language Intelligence4 versions - Latest release: 6 months ago - 42 downloads last month - 1 maintainer
toklens 0.1.2
TokLens: Looking Beyond Fertility in Tokenizer Evaluation2 versions - Latest release: 6 months ago - 8 downloads last month - 1 stars on GitHub - 1 maintainer
ailang-cli 1.0.3
AI-Native Programming Language - Write code in natural language2 versions - Latest release: 6 months ago - 26 downloads last month - 1 stars on GitHub - 1 maintainer
yasbd-lib 1.0.3
A high-accuracy, rule-based Sentence Boundary Detector (SBD) with a drop-in adapter for pysbd, de...29 versions - Latest release: 12 days ago - 7.55 thousand downloads last month - 34 stars on GitHub - 1 maintainer
chunklet-py 3.0.1
High-fidelity context-aware chunking and interactive visualization for RAG. Advanced segmentation...17 versions - Latest release: 21 days ago - 403 downloads last month - 88 stars on GitHub - 1 maintainer
wordninja-pp 0.3.1
Probabilistically split concatenated words across 90 languages β incl. English, Spanish, French, ...3 versions - Latest release: 5 months ago - 469 downloads last month - 1 maintainer
batch-translator 4.1.0
ζΉιηΏ»θ―ζθ½ζζ‘£ηε€θ―θ¨ηΏ»θ―ε·₯ε ·1 version - Latest release: 6 months ago - 113 downloads last month - 0 stars on GitHub - 1 maintainer
spekoai 0.2.2
Official Speko Python SDK β one API, every voice provider7 versions - Latest release: 14 days ago - 250 downloads last month - 2 stars on GitHub - 1 maintainer
blackmagic-retrieval 0.1.0
Cross-lingual sparse retrieval + reasoning + GA imagination over typed concept anchors (EN/JA/KO).1 version - Latest release: 6 months ago - 1 maintainer
contextgem 1.1.0
Extract structured data and insights from documents using LLMs and decision models53 versions - Latest release: 6 days ago - 11.8 thousand downloads last month - 2,011 stars on GitHub - 1 maintainer
toksight 0.3.0
Tokenizer analysis toolkit. Compare vocabulary coverage, compression ratios, and token boundaries...2 versions - Latest release: 7 months ago - 13 downloads last month - 1 stars on GitHub - 1 maintainer
Top 3.3% on pypi.org
55 versions - Latest release: 8 months ago - 13 dependent packages - 303 dependent repositories - 340 thousand downloads last month - 323 stars on GitHub - 1 maintainer
mkdocs-static-i18n 1.3.1 π°
MkDocs i18n plugin using static translation markdown files55 versions - Latest release: 8 months ago - 13 dependent packages - 303 dependent repositories - 340 thousand downloads last month - 323 stars on GitHub - 1 maintainer
xqasem 0.1.2
Cross-lingual QASem parser for predicate-centered question-answer structures.3 versions - Latest release: 6 months ago - 64 downloads last month - 0 stars on GitHub - 1 maintainer
omnilingual-asr 0.2.0
Omnilingual ASR Modeling Library2 versions - Latest release: 10 months ago - 5.26 thousand downloads last month - 2,949 stars on GitHub - 1 maintainer
naijaeval 0.1.0
Evaluation toolkit for AI systems in African language contexts β code-switching, dialectal robust...1 version - Latest release: 6 months ago - 114 downloads last month - 0 stars on GitHub - 1 maintainer
omnivoice 0.2.1
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models8 versions - Latest release: 3 months ago - 133 thousand downloads last month - 14,649 stars on GitHub - 1 maintainer
lahgtna-omnivoice 0.1.5
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models1 version - Latest release: 6 months ago - 35 downloads last month - 14,649 stars on GitHub - 1 maintainer
filenthropist 0.3.1
Local-first file scanner and labeler that lets you work safely with autonomous AI agents. Multili...2 versions - Latest release: 6 months ago - 68 downloads last month - 1 stars on GitHub - 1 maintainer
abogen 1.3.1 π°
Generate audiobooks from EPUBs, PDFs and text with synchronized captions.28 versions - Latest release: 9 months ago - 1.13 thousand downloads last month - 6,128 stars on GitHub - 1 maintainer
wiktextract 1.99.7
Wiktionary dump file parser and multilingual data extractor8 versions - Latest release: over 4 years ago - 4 dependent repositories - 477 downloads last month - 1,285 stars on GitHub - 1 maintainer
pywsd-datasets 0.2.0
Unified Word Sense Disambiguation benchmark datasets, normalized to modern wn lexicon sense IDs (...2 versions - Latest release: 6 months ago - 105 downloads last month - 0 stars on GitHub - 1 maintainer
feluda 0.10.0 π°
A configurable engine for analysing multi-lingual and multi-modal content.7 versions - Latest release: about 1 year ago - 125 downloads last month - 96 stars on GitHub - 1 maintainer
Related Keywords
nlp
101
python
52
translation
39
llm
32
i18n
31
tts
29
ai
26
text-to-speech
23
machine-learning
22
tokenizer
19
rag
18
speech-to-text
18
natural-language-processing
18
language
17
speech-synthesis
15
onnx
15
deep-learning
14
ner
14
text-processing
14
localization
14
transcription
13
openai
12
tokenization
12
evaluation
12
audio
12
django
12
streaming
12
api
12
internationalization
12
pytorch
11
arabic
11
natural language processing
11
zero-shot
11
speech
11
embeddings
11
multimodal
10
voice-cloning
10
linguistics
10
stt
10
language-detection
10
chinese
10
english
10
transformers
10
machine-translation
9
library
9
asr
9
NLP
9
benchmark
8
speech-recognition
8
analysis
8
python3
8
mcp
8
ocr
8
information-extraction
7
cli
7
analyzer
7
morphological
7
privacy
7
artificial-intelligence
7
japanese
7
whisper
7
huggingface
7
text-analysis
7
realtime
6
french
6
sentence-transformers
6
retrieval
6
embedding
6
text-classification
6
deep learning
6
linux
6
search
6
chatbot
6
nlp-library
6
ai-agents
6
low-resource
6
language-model
6
langchain
6
bert
6
dataset
6
machine learning
6
sentence-segmentation
5
spanish
5
mcp-server
5
text
5
sentence-boundary-detection
5
entity-extraction
5
agents
5
languages
5
anthropic
5
speech recognition
5
indian-languages
5
sdk
5
ai-safety
5
natural-language
5
knowledge-graph
5
visualization
5
hindi
5
claude
5
rust
5