๐ Subscribe to ๐ธCoqui's Newsletter
Coqui STT (๐ธSTT) is a fast, open-source, multi-platform, deep-learning toolkit for training and deploying speech-to-text models. ๐ธSTT is battle tested in both production and research ๐
- 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.
Type | Link |
---|---|
๐จ Bug Reports | Github Issue Tracker |
๐ Feature Requests & Ideas | Github Issue Tracker |
โ Questions | Github Discussions |
๐ฌ General Discussion | Github Discussions or Gitter Room |
Type | Link |
---|---|
๐ฐ Documentation | stt.readthedocs.io |
๐ Latest release with pre-trained models | see the latest release on GitHub |
๐ค Contribution Guidelines | CONTRIBUTING.rst |