STT

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This project is no longer actively maintained, and we have stopped hosting the online Model Zoo.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](https://github.com/openai/whisper), and have ourselves focused on [Coqui TTS](https://github.com/coqui-ai/TTS) and [Coqui Studio](https://coqui.ai/).

The models will remain available in [the releases of the coqui-ai/STT-models repo](https://github.com/coqui-ai/STT-models/releases).

Subscribe to ?Coqui's Newsletter

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

?STT 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

Where to Ask Questions

Type	Link
Bug Reports	Github Issue Tracker
? Feature Requests & Ideas	Github Issue Tracker
❔ Questions	Github Discussions
General Discussion	Github Discussions or Gitter Room

Links & Resources

Type	Link
? Documentation	stt.readthedocs.io
Latest release with pre-trained models	see the latest release on GitHub
? Contribution Guidelines	CONTRIBUTING.rst