Parallel Processing for Speeding-up a Voice Assistant with Google Gemini
Previously, I built a Google Gemini-powered voice assistant (chatbot) with Python. However, in that project, I used sequential (programming) processing such that there was a pause in the middle of the reply from AI. In this video, I will show you how to build a Google Gemini-powered voice assistant with parallel processing in Python. Specifically, we will use parallel computing in Python to split tasks such as text generation, text-to-speech conversation, and audio playing onto three threads (multithreading) and accelerate the program. I have one version of the code that only works on Raspberry Pi because it requires LEDs and resistors. If you do not have LEDs or resistors, I have another version that works on Raspberry Pi and Windows PC.
Please check the GitHub page for the Python code and additional packages here:
https://github.com/techmakerai/Parall...
Here is the link to my previous video in which I talked about the Google Gemini API key,
• Build a Google Gemini Powered Voice Assist...
Hardware:
1. Raspberry Pi (https://amzn.to/4bmstJa)
2. microSD card (https://amzn.to/4ay0HbY)
3. Audio amplifier (https://amzn.to/3JjPWy9)
4. Mini speaker (https://amzn.to/3TB9Pp3)
5. USB Microphone (https://amzn.to/3HGGSCA)
6. (optional) LEDs and resistors (https://amzn.to/3Jg4Yoz)
7. (optional) Breadboard (https://amzn.to/3V3ruWY)
If you found my videos helpful, please consider supporting my channel at:
https://www.buymeacoffee.com/techmakerai
#googlegemini #voiceassistant #parallel #parallelprocessing #raspberrypi #chatbot #multithreading #python #gemini #pythontutorial #largelanguagemodels #ai #aichatbots #raspberrypiprojects #raspberrypi4 #api #programming #tutorial #pythonprogramming #python3 #pythonprojects