Mozilla's DeepSpeech project[1] is using TensorFlow and some paper from Baidu to make an open source speech to text system, based on deep learning (TensorFlow). The current project allow the training for own local datasets, but also there is a pre-trained model that can be used during the development.

The goal of the project is:

  • Connect to mumble or to the local audio stream
  • Connect to etherpad
  • Map the sound to text, and write it into the etherpad
  • Have fun how funny accents break the system
  • Redo the etherpad based on what you remember from the meeting and send it to the RESULT mailing list

[1] https://github.com/mozilla/DeepSpeech

Looking for hackers with the skills:

speech tensorflow

This project is part of:

Hack Week 17

Activity

  • almost 3 years ago: mbrugger liked this project.
  • almost 3 years ago: aplanas started this project.
  • almost 3 years ago: ancorgs liked this project.
  • almost 3 years ago: aplanas added keyword "speech" to this project.
  • almost 3 years ago: aplanas added keyword "tensorflow" to this project.
  • almost 3 years ago: aplanas originated this project.

  • Comments

    Be the first to comment!

    Similar Projects

    Ambrogio - a privata consierge for you and your pets by rsblendido

    [comment]: # (Please use the project descriptio...


    FuseML - accelerate your Hack Week ML projects by stefannica

    [comment]: # (Please use the project descriptio...