SeeRepo
Draw my repo

FunASR vs PaddleOCR

FunASR and PaddleOCR share 9 technologies: FastAPI, uvicorn, lifecycle-runtime-ktx, constraintlayout, ui-graphics, sentencepiece, onnxruntime, ONNX, and beautifulsoup4. FunASR is written in Python and PaddleOCR in C++.

Read it as markdown

What they share and what sets them apart

modelscope

FunASR

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

Python20.9kRead on November 5, 2026, at commit fd1d4aaWhat is FunASR built with?

Only in FunASR

In common

PaddlePaddle

PaddleOCR

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

C++92.3kRead on November 4, 2026, at commit dab3fe3What is PaddleOCR built with?

Only in PaddleOCR

Side by side

SizeLines written by people and agents, without generated ones; code files, without tests.
FunASR278,515 lines written1,165 code files
PaddleOCR153,989 lines written706 code files
Who writes itA commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
FunASR3.3% of its commits signed by AIWith Codex, Claude Code, and Gemini CLI
PaddleOCR0.3% of its commits signed by AIWith Claude Code, Cursor, and GitHub Copilot
ActivityFrom GitHub and its history, on the day SeeRepo read it.
FunASRLast push November 5, 20264,986 commits20,948 stars
PaddleOCRLast push September 16, 20265,137 commits92,256 stars
TestsThe files that test the code, and the share of code files a test imports.
FunASR202 test files0.9% of its code files have a test that imports them
PaddleOCR105 test files11% of its code files have a test that imports them

Frequently asked questions

Which is bigger, FunASR or PaddleOCR?
FunASR, with 278,515 lines written; PaddleOCR has 153,989.

The proof: modelscope/FunASR's code at commit fd1d4aa

Which has more GitHub stars, FunASR or PaddleOCR?
PaddleOCR, with 92,256 stars; FunASR has 20,948.

The proof: PaddlePaddle/PaddleOCR on GitHub

Which has more tests, FunASR or PaddleOCR?
FunASR, with 202 test files; PaddleOCR has 105.

The proof: modelscope/FunASR's code at commit fd1d4aa

Which was updated more recently, FunASR or PaddleOCR?
FunASR: its last push was on November 5, 2026, and PaddleOCR's on September 16, 2026.

The proof: modelscope/FunASR's commits on GitHub

Which has more commits signed by AI, FunASR or PaddleOCR?
FunASR: an AI signed 3.3% of its commits, with Codex, Claude Code, and Gemini CLI; in PaddleOCR, 0.3%.

The proof: the commits each tool signed in modelscope/FunASR

See inside your code, today.

Paste your repo and see it drawn, part by part: a medium one in under a minute.

Free, no account.

Or look inside SeeRepo's own →