liuhuayong/ollama-voice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
ollama-voice project
2 Commits 1 Branch 0 Tags 61 KiB
Python 100%
96c3b0feb9
Go to file
M 96c3b0feb9 First version
2023-11-12 02:49:10 +01:00
.gitignore First version 2023-11-12 02:49:10 +01:00
assistant.py First version 2023-11-12 02:49:10 +01:00
assistant.yaml First version 2023-11-12 02:49:10 +01:00
LICENSE Initial commit 2023-11-12 02:12:33 +01:00
README.md First version 2023-11-12 02:49:10 +01:00
requirements.txt First version 2023-11-12 02:49:10 +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

Todo

  • Allow a full conversation with a "press to talk" function between requests
  • Process ollama json responses in stream mode to generate voice at the end of each sentence.