Contents Menu Expand
Coqui STT 1.4.0 documentation
Light Logo Dark Logo

Quick Reference

  • Deployment / Inference
    • Supported platforms
  • Training: Quickstart
  • Training: Advanced Topics
    • Command-line flags for the training scripts
    • Bootstrap from a pre-trained model
    • Automatic Mixed Precision
    • Checkpointing
    • Common Voice training data
    • Training Data Augmentation
    • Exporting a model for deployment
    • Model Geometry
    • Data Importers
    • Inference tools in the training package
  • Building Binaries

API Reference

  • Error codes
  • C API
    • Data structures
  • .NET Framework
  • Java
  • JavaScript (NodeJS / ElectronJS / WASM)
  • Python

Examples

  • Python API Usage example
  • JavaScript API Usage example
  • C API Usage example
  • .NET API Usage example
  • Java API Usage example
  • Hot-word boosting API Usage example
  • User contributed examples

Language Model

  • How to Train a Language Model

STT Playbook

  • Coqui STT Playbook

Advanced topics

  • Beam search decoder
  • Decoder API reference
  • Parallel Training Optimization

Training: Advanced Topics¶

This document contains more advanced topics with regard to training models with STT. If you’d prefer a lighter introduction, please refer to Training: Quickstart.

  • Command-line flags for the training scripts
  • Bootstrap from a pre-trained model
  • Automatic Mixed Precision
  • Checkpointing
  • Common Voice training data
  • Training Data Augmentation
  • Exporting a model for deployment
  • Model Geometry
  • Data Importers
  • Inference tools in the training package
Next
Command-line flags for the training scripts
Previous
Training: Quickstart
Copyright © 2021 Coqui GmbH, 2020 DeepSpeech authors, 2019-2020 Mozilla Corporation | Built with Sphinx and @pradyunsg's Furo theme. | Show Source