Source: https://seerepo.com/r/PaddlePaddle/PaddleSpeech
Markdown source: https://seerepo.com/r/PaddlePaddle/PaddleSpeech.md
Description: PaddlePaddle/PaddleSpeech is a Python repo with 195,799 lines written. PaddleSpeech is built with FastAPI, starlette, and uvicorn.

# What's inside PaddlePaddle/PaddleSpeech

PaddlePaddle/PaddleSpeech is a Python repo with 195,799 lines written. PaddleSpeech is built with FastAPI, starlette, and uvicorn.

Its description on GitHub: “Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.”

Python · Apache-2.0 · 12,706 stars · GitHub: https://github.com/PaddlePaddle/PaddleSpeech

Read on November 10, 2026, at commit 6b25a40.

## More on this repo

- [What is PaddleSpeech built with?](https://seerepo.com/r/PaddlePaddle/PaddleSpeech/built): PaddleSpeech is built with FastAPI, starlette, and uvicorn.
- [How much of PaddleSpeech did AI write?](https://seerepo.com/r/PaddlePaddle/PaddleSpeech/ai): No AI tool signed any of the 3,606 commits of PaddleSpeech.

## In figures

- 195,799 lines written: The ones people and agents wrote: product, tests, schemas and tooling. Generated code doesn’t count.
- 872 source files: The same as the lines: product, tests, schemas and tooling. What’s generated doesn’t count.
- 104 test files: The files that test the code.
- 10 technologies: Each service with the file and line that prove it.

SeeRepo read the facts in its code and kept none of it. AI only helps sort its packages and folders by their names, and never sees its code.

## Frequently asked questions

### What is PaddlePaddle/PaddleSpeech?

PaddlePaddle/PaddleSpeech is a Python repo with 195,799 lines written. Its description on GitHub: “Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.”

The proof: [its page on GitHub](https://github.com/PaddlePaddle/PaddleSpeech)

### What is PaddleSpeech built with?

PaddleSpeech is built with FastAPI, starlette, and uvicorn.

The proof: [each service with its file and line](https://seerepo.com/r/PaddlePaddle/PaddleSpeech/built)

### What license does PaddleSpeech have?

PaddleSpeech is released under the Apache-2.0 license.

The proof: [its page on GitHub](https://github.com/PaddlePaddle/PaddleSpeech)

### How many stars does PaddleSpeech have on GitHub?

PaddleSpeech had 12,706 stars on GitHub on November 10, 2026.

The proof: [its page on GitHub](https://github.com/PaddlePaddle/PaddleSpeech)

## Add this badge to your README

It links to this page and updates itself each time SeeRepo reads the repo.

```markdown
[![PaddlePaddle/PaddleSpeech on SeeRepo](https://seerepo.com/badge/PaddlePaddle/PaddleSpeech.svg)](https://seerepo.com/r/PaddlePaddle/PaddleSpeech?de=insignia)
```

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.