Fork of Priler/jarvis (CC BY-NC-SA 4.0)
https://github.com/Priler/jarvis
| Crysis2 Sounds | ||
| custom-commands | ||
| Jarvis Sound Pack | ||
| pv_custom_keywords | ||
| sound | ||
| utils | ||
| .gitignore | ||
| _stt.py | ||
| config.py | ||
| latest_silero_models.yml | ||
| main.py | ||
| main_old.py | ||
| README.md | ||
| requirements.txt | ||
| speech.wav | ||
| stt.py | ||
| stt_google.py | ||
| stt_picovoice.py | ||
| stt_vosk.py | ||
| tts.py | ||
Kesha v3.0 very early (aka Jarvis update)
Simple Voice Assistant made as an experiment using Silero & Vosk.
Later on Picovoice Porcupine Wake Word Detection & ChatGPT was added.
The code has NOT been polished and is provided "as is". There are a lot of code that are redundant and there are tons of improvements that can be made.
Installation
First, install the requirements, the file is just a pip freeze 'k.
Second, check config.py and set required values.
Next, just run the main.py script.
And don't forget to put models of Vosk to main folder.
You can get the latest from the official website.
The one I was using is small.
Author
(2022) Abraham Tugalov