Skip to content

DeepASR Module

Lucie Galland edited this page Jul 19, 2024 · 3 revisions

An ASR can be used to communicate orally with greta, the DeepASR module implements an interface between Greta and a python AST

Intergrated ASRs

Currently only DeepGram is implemented

Create a new DeepASR module

To create a new DeepASR module,

  • Create a class in the auxiliary project DeepASR that extends DeepASRFrame
  • Create a new folder in Common/Data/DeepASR/{Yourmodelname} Copiyng the files in Common/Data/DeepASR/DeepGram
  • Modify the copy of DeepGram.py with the code to access your LLM model, the final answer should be printed by your python module after "Speech Final:"
  • Modify requirements.txt with your requirements
  • Modify check_env.py and init_env.bat with a new conda environment name
  • In the java class, initiate the strings DeepASR_python_env_checker_path, DeepASR_python_env_installer_path ,python_asr_path with the appropriate relative paths
  • Add your new Module in Modular.xml

Getting started with Greta

Greta Architecture

Quick start

Advanced

Functionalities

Core functionality

Auxiliary functionalities

Preview functionality

Nothing to show here

Previous functionality (possibly it still works, but not supported anymore)

Clone this wiki locally