Daktilograf 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
- High-quality of 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 |
|---|---|
| 🚨 Bug Reports | Github Issue Tracker |
| 🎁 Feature Requests & Ideas | Github Issue Tracker |
| ❔ Questions | Github Discussions |
| 💬 General Discussion | Github Discussions |
| Type | Link |
|---|---|
| 📰 Documentation | daktilograf3.readthedocs.io |
| 🚀 Latest release with pre-trained models | see the latest release on GitHub |
| 🤝 Contribution Guidelines | CONTRIBUTING.rst |
