# PaddlePaddle/models

Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

Repository: https://github.com/PaddlePaddle/models
Canonical: https://ross.abutalabs.com/products/paddlepaddle-models
Language: Python
License: Apache-2.0
License Family: permissive
Topics: paddlepaddle, deep-learning, neural-network, computer-vision, natural-language-processing, recommendation, speech, nlp, cv, models
Last push: 2025-01-15T17:54:36+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 1, release rhythm 8, longevity 100
- inputs: {"age_days": 3422, "days_push": 595, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6932, forks 2856 (observed 2026-08-28T04:09:51.491040+00:00)

## What it is
PaddlePaddle's officially maintained industry-grade model repository containing 600+ models across computer vision, NLP, speech, recommendation, and time series. It provides end-to-end development suites for tasks like image classification, object detection, OCR, and speech synthesis, built on the PaddlePaddle deep learning framework.

## Use cases
- find pretrained models for image classification
- run object detection with PaddlePaddle
- OCR text recognition models
- speech synthesis and recognition models
- recommendation system models
- semantic understanding NLP models
- deploy production deep learning models in Chinese industry settings

## When to choose
- you use the PaddlePaddle framework and need well-tested official models
- you need production-proven models with vendor support
- you work on CV, NLP, speech, or recommendation tasks
- you want competition-winning model implementations

## When to avoid
- you use PyTorch or TensorFlow instead of PaddlePaddle
- you need only lightweight inference without the Paddle ecosystem
- you want the latest research models before they are ported

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, nlp, speech-recognition, tts, computer-vision
- domain: deep-learning, computer-vision, speech-processing, machine-learning
- platform: python, cross-platform
- tags: paddlepaddle, model-zoo, pretrained-models, recommendation, time-series, large-models, model-library, natural-language-processing, gpu

## Member repositories
- PaddlePaddle/models (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:51.491040+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 2026-08-29T17:41:15.585555+00:00, confidence not recorded.
  - readme: https://github.com/PaddlePaddle/models (fetched 2026-08-28T04:09:51.491040+00:00, sha 3695e7f61e22)
- Data as of 2026-08-30T08:39:29.467469+00:00.