Skip to content

About

A simple chatbot based on asr, tts, and llm.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 

Repository files navigation

LLM-based-Chatbot

A simple voice chatbot built on ASR -> LLM -> TTS. Press Enter to record your speech, the audio is transcribed by PaddleSpeech, answered by a local LLM served through Ollama (qwen2.5:7b), and the reply is synthesized and played back.

Requirements

1. Hardware / system dependencies

A GPU is required — the ASR is hard-coded to run on device='gpu', and the PaddlePaddle build installed by install.sh targets CUDA 12.0.

  • NVIDIA GPU with a driver supporting CUDA 12.0
  • sox (provides the rec command used for recording)
  • alsa-utils (provides the aplay command used for playback)
sudo apt update
sudo apt install -y sox alsa-utils

2. Conda environment

Python 3.10 is recommended:

conda create -n llm python=3.10
conda install -n llm -c conda-forge cudnn=8.9.7.29
conda activate llm

3. Python dependencies

sh install.sh

This installs PaddleSpeech (ASR + TTS), LangChain and the Ollama integration.

4. Ollama and the LLM model

# install Ollama first
ollama pull qwen2.5:7b

Usage

Run the following script to chat with LLM:

conda activate llm
python voice_assistant.py

About

A simple chatbot based on asr, tts, and llm.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages