liuhuayong/ollama-voice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
ollama-voice project
5 Commits 1 Branch 0 Tags 61 KiB
Python 100%
202accc7af
Go to file
M 202accc7af Fix requests and update readme
2023-11-12 19:02:41 +01:00
.gitignore First version 2023-11-12 02:49:10 +01:00
assistant.png Push to talk, basic UI and ollama response stream 2023-11-12 18:28:47 +01:00
assistant.py Fix requests and update readme 2023-11-12 19:02:41 +01:00
assistant.yaml Fix requests and update readme 2023-11-12 19:02:41 +01:00
LICENSE Initial commit 2023-11-12 02:12:33 +01:00
README.md Fix requests and update readme 2023-11-12 19:02:41 +01:00
requirements.txt Push to talk, basic UI and ollama response stream 2023-11-12 18:28:47 +01:00

README.md

ollama-voice

Plug whisper audio transcription to a local ollama server and ouput tts audio responses

This is just a simple combination of three tools in offline mode:

  • Speech recognition: whisper running local models in offline mode
  • Large Language Mode: ollama running local models in offline mode
  • Offline Text To Speech: pyttsx3

Prerequisites

whisper dependencies are setup to run on GPU so Install Cuda before running pip install.

Running

Install ollama and ensure server is started locally first (in WLS under windows) (e.g. curl https://ollama.ai/install.sh | sh)

Download a whisper model and place it in the whisper subfolder (e.g. e5b1a55b89/large-v3.pt)

Configure assistant.yaml settings. (It is setup to work in french with ollama mistral model by default...)

Run assistant.py

Leave space key pressed to talk, the AI will interpret the query when you release the key.

Todo

  • Fix the prompt
  • Rearrange code base
  • Some audio visualization in the UI
  • Multi threading to overlap queries/rendering with response generation