https://github.com/assemblyai-community/realtime-voice-command-recognition

Build your own real-time voice command recognition model with TensorFlow
https://github.com/assemblyai-community/realtime-voice-command-recognition

Last synced: 3 months ago
JSON representation

Build your own real-time voice command recognition model with TensorFlow

• Host: GitHub
• URL: https://github.com/assemblyai-community/realtime-voice-command-recognition
• Owner: AssemblyAI-Community
• Created: 2022-07-22T13:42:57.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2022-07-22T15:52:09.000Z (almost 4 years ago)
• Last Synced: 2024-06-24T19:02:44.147Z (about 2 years ago)
• Language: Python
• Size: 1.81 MB
• Stars: 33
• Watchers: 4
• Forks: 21
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Realtime Voice Command Recognition

Build your own real-time voice command recognition model with TensorFlow.

**Watch the video tutorial:**

[![Alt text](https://img.youtube.com/vi/m-JzldXm9bQ/hqdefault.jpg)](https://youtu.be/m-JzldXm9bQ)

## Instructions

- Run the Colab from [this TensorFlow tutorial](https://www.tensorflow.org/tutorials/audio/simple_audio)

- Follow the video to zip and download the trained model

- Make sure to use the correct `commands` order in `main.py` (same as when running the Colab)

- Install pyaudio and tensorflow

- Extraxt the zip to a folder named `saved_model`

- Run `python main.py`

## Screenshot

![Demo](demo.png)