Hindi Python Packages

vindex

Evals for Indian-language LLM apps: script adherence, mistranslation checks, calibrated similarity and an Indic LLM judge

pipecat-mirai

Mirai for Pipecat: Hindi, Hinglish and Gujarati text-to-speech, the Realtime API (speech to speech), and smooth phone-call audio

krutiextract

A universal Python CLI toolkit to seamlessly extract legacy Hindi PDFs (KrutiDev, Devlys, Chanakya) into perfect Markdown. Features AI auto-detection, NLTK English shielding, and OpenCV-enhanced OCR.

follow-through

Finds the commitments people make out loud in a meeting transcript and tracks them until they are closed. Reads English and Hinglish. Runs entirely on your machine.

anyscribecli

Turn YouTube, Instagram and audio into searchable notes, including Hindi and Hinglish. CLI, local dashboard and MCP server.

polywhisper

🎙️ PolyWhisper v9: efficient multilingual Indic ASR — frozen Whisper-Small + per-language LoRA for Hindi, Tamil, Telugu, Bengali, Marathi. Bengali −34.5%, Marathi −43.2% vs baseline. ONNX CPU-ready. Apache-2.0.

indicate

transliterate hindi, punjabi to english

anyscribe

Turn YouTube, Instagram and audio into searchable notes, including Hindi and Hinglish. CLI, local dashboard and MCP server.

indicorderbench

Catches multilingual voice agents placing the wrong order. τ-bench style benchmark + CI gate for voice ordering agents in English and Hinglish: checks the committed order, not the transcript.

lipi-aparsoft

Python toolkit to decode legacy Hindi font-encoded PDFs (KrutiDev, Chanakya, DevLys) into Unicode Devanagari. Built for Hindi PDF & govt document ingestion pipelines.

studio99

Official Python client for the Studio99 Indic Typography API

akshara-tokenizer

Akshara-aware tokenizer for six Brahmic scripts, with a trained SentencePiece model

anuvaad

State of the art open-source translation for Indic languages.

pranaam

pranaam: predict religion based on name

youtube-dubber

Real-time video dubber: translates and dubs YouTube videos into Hindi + 19 languages using Whisper, Groq, and edge-tts. Runs locally.

quanfire-multilingual-embedding

Indic-first embeddings you can actually ship. Documented sources. Weights: CC BY-SA 4.0.

hindi-readability

First practical Python implementation of Devanagari-aware Hindi text readability scoring. Pearson r=0.81 · 49-sentence corpus · 3 original formulas · Zero dependencies

deeptranslit

Efficient and easy to use transliteration for Indian languages

dhwani

English to Indic language phonetic conversion engine

loit

Lot Of Indic Tweets

hindi-normalize

Convert Hindi number words to digits and normalize Devanagari ASR/OCR text — zero-dependency

shilp

Shilp is a programming language in which most of the instructions are written in Hindi. The language is a descendent of Python. Shilp stands for Sahaj Hindi Lipi Prakalp.......

num2wordshindi

python program to convert number to hindi strings