Skip to content
ํ”„๋กœ์ ํŠธ

coqui-ai/STT has 2,604 GitHub stars and 295 forks. GitHot measured 0 stars in 24 hours, 0 in 7 days, and +1 in 15 days. Last checked 2026-11-19 01:53 UTC. Last push 2024-03-11.

์ด ์ˆ˜์น˜๋ฅผ ์ธก์ •ํ•˜๋Š” ๋ฐฉ๋ฒ•

What you can do

  • High-quality pre-trained STT model.
  • Efficient training pipeline with Multi-GPU support.
  • Streaming inference.
  • Multiple possible transcripts, each with an associated confidence score.

์ธก์ •๋œ ์Šคํƒ€ ์ฆ๊ฐ€

in 24h
0
in 7 days
0
in 15 days
+1
in 1 month
๊ธฐ๋ก ์ˆ˜์ง‘ ์ค‘

์„œ๋กœ ๊ฒน์น˜๋Š” ๊ธฐ๊ฐ„์˜ ์ˆœ์ฆ๊ฐ€๋Ÿ‰์ด๋ฉฐ ์ผ๋ณ„ ํ•ฉ๊ณ„๊ฐ€ ์•„๋‹™๋‹ˆ๋‹ค. ์ธก์ •๊ฐ’์ด ์—†์œผ๋ฉด ๋น„์›Œ ๋‘ก๋‹ˆ๋‹ค. ์Šคํƒ€๋Š” ๊ด€์‹ฌ๋„๋ฅผ ๋‚˜ํƒ€๋‚ด๋ฉฐ ํ’ˆ์งˆ์„ ๋ณด์žฅํ•˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.

์†Œ๊ฐœ

๐ŸธSTT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

๋จธ์‹ ๋Ÿฌ๋‹

README.md

Original

.. note:: This project is no longer actively maintained, and we have stopped hosting the online Model Zoo. We've seen focus shift towards newer STT models such as Whisper, and have ourselves focused on Coqui TTS and Coqui Studio.

The models will remain available in the releases of the coqui-ai/STT-models repo.

.. image:: images/coqui-STT-logo-green.png :alt: Coqui STT logo

.. |doc-img| image:: https://readthedocs.org/projects/stt/badge/?version=latest :target: https://stt.readthedocs.io/?badge=latest :alt: Documentation

.. |covenant-img| image:: https://img.shields.io/badge/Contributor%20Covenant-2.0-4baaaa.svg :target: CODE_OF_CONDUCT.md :alt: Contributor Covenant

.. |gitter-img| image:: https://badges.gitter.im/coqui-ai/STT.svg :target: https://gitter.im/coqui-ai/STT?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge :alt: Gitter Room

.. |doi| image:: https://zenodo.org/badge/344354127.svg :target: https://zenodo.org/badge/latestdoi/344354127

|doc-img| |covenant-img| |gitter-img| |doi|

๐Ÿ‘‰ Subscribe to ๐ŸธCoqui's Newsletter <https://coqui.ai/?subscription=true>_

Coqui STT (๐ŸธSTT) is a fast, open-source, multi-platform, deep-learning toolkit for training and deploying speech-to-text models. ๐ŸธSTT is battle tested in both production and research ๐Ÿš€

๐ŸธSTT features

  • High-quality pre-trained STT model.
  • Efficient training pipeline with Multi-GPU support.
  • Streaming inference.
  • Multiple possible transcripts, each with an associated confidence score.
  • Real-time inference.
  • Small-footprint acoustic model.
  • Bindings for various programming languages.

Quickstart <https://stt.readthedocs.io/en/latest/#quickstart>_

Where to Ask Questions

.. list-table:: :widths: 25 25 :header-rows: 1

    • Type
    • Link
    • ๐Ÿšจ Bug Reports
    • Github Issue Tracker <https://github.com/coqui-ai/STT/issues/>_
    • ๐ŸŽ Feature Requests & Ideas
    • Github Issue Tracker <https://github.com/coqui-ai/STT/issues/>_
    • โ” Questions
    • Github Discussions <https://github.com/coqui-ai/stt/discussions/>_
    • ๐Ÿ’ฌ General Discussion
    • Github Discussions <https://github.com/coqui-ai/stt/discussions/>_ or Gitter Room <https://gitter.im/coqui-ai/STT?utm_source=share-link&utm_medium=link&utm_campaign=share-link>_

Links & Resources

.. list-table:: :widths: 25 25 :header-rows: 1

    • Type
    • Link
    • ๐Ÿ“ฐ Documentation
    • stt.readthedocs.io <https://stt.readthedocs.io/>_
    • ๐Ÿš€ Latest release with pre-trained models
    • see the latest release on GitHub <https://github.com/coqui-ai/STT/releases/latest>_
    • ๐Ÿค Contribution Guidelines
    • CONTRIBUTING.rst <CONTRIBUTING.rst>_