# kakaobrain/pororo

PORORO: Platform Of neuRal mOdels for natuRal language prOcessing

Repository: https://github.com/kakaobrain/pororo
Canonical: https://ross.abutalabs.com/products/pororo
Homepage: https://kakaobrain.github.io/pororo
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, natural-language-processing, automatic-speech-recognition, speech-synthesis, neural-models
Archived: true
Last push: 2022-03-23T05:55:06+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2043, "days_push": 1624, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1305, forks 217 (observed 2026-08-28T04:04:18.595648+00:00)

## What it is
PORORO is a Python library from Kakao Brain that provides unified access to dozens of pretrained neural models for natural language processing and speech tasks, including translation, summarization, QA, ASR, and TTS. It lets users run many subtasks by simply passing a task name to a single Pororo interface.

## Use cases
- run korean nlp tasks with pretrained models
- translate text between languages in python
- convert speech to text
- text to speech synthesis
- summarize long documents
- extract named entities from text
- question answering over a passage
- pos tagging and tokenization for korean

## When to choose
- you need many NLP or speech subtasks behind one simple API
- you work with Korean or multilingual text
- you want pretrained models without building pipelines yourself

## When to avoid
- you need a maintained library with recent updates
- you require the latest transformer models or Hugging Face ecosystem integration
- you need production ASR/TTS without extra external dependencies like wav2letter

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, speech-recognition, tts, machine-learning, ocr, deep-learning
- domain: speech-processing, deep-learning, machine-learning
- platform: python, cross-platform
- tags: korean-nlp, multilingual, pretrained-models, pytorch, kakaobrain, machine-translation, text-summarization, named-entity-recognition, natural-language-processing, linux

## Member repositories
- kakaobrain/pororo (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:18.595648+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 2026-08-30T04:51:02.923009+00:00, confidence not recorded.
  - readme: https://github.com/kakaobrain/pororo (fetched 2026-08-28T04:04:18.595648+00:00, sha e74822f0f7ba)
  - homepage: https://kakaobrain.github.io/pororo (fetched 2026-08-29T12:08:58.095728+00:00, sha 96c0aa3814b0)
  - registry_pypi: https://pypi.org/pypi/pororo/json (fetched 2026-08-29T12:08:58.098115+00:00, sha 084c144f6bac)
- Data as of 2026-08-30T08:39:29.467469+00:00.