GithubHelp home page GithubHelp logo

chatgpt-conversation's Introduction

chatgpt-conversation

Have a conversation with ChatGPT using your voice, and have it talk back.

Requirements (Ubuntu)

  • espeak
  • ffmpeg
  • portaudio19-dev
  • python3-pyaudio

To install all of them:

sudo apt install portaudio19-dev python3-pyaudio ffmpeg espeak

Installation

Copy config.json.example to config.json and fill in the session_token value following the guide here.

Also, install requirements:

pip install -r requirements.txt

Usage

Run chatgpt.py, and wait 2 seconds before starting the conversation (this is to normalise ambient noise). You can keep responding to ChatGPT, it's all 1 "conversation".

Next steps

  • Cut-off ChatGPT as it's speaking if you decide to interrupt.
  • Silence PyAudio errors.
  • Remove common, useless end phrases from ChatGPT ("I am an online LLM...", etc.).
  • Make this as a web-app (better text-to-speech, universal):
    • Create interface
    • Create backend
    • Hook-up to a GPU so it's faster (in the speech->text bit).

chatgpt-conversation's People

Contributors

platelminto avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

chatgpt-conversation's Issues

Telegram

Could you integrate this into a telegram bot?

No module named 'speech_recognition'

I run into this problem everytime i try running it

Traceback (most recent call last):
  File "C:\Users\Mauro Araripe\Documents\Projetos\chatgpt-conversation\chatgpt.py", line 4, in <module>
    from record import SpeechRecognizer
  File "C:\Users\Mauro Araripe\Documents\Projetos\chatgpt-conversation\record.py", line 4, in <module>
    import speech_recognition as sr
ModuleNotFoundError: No module named 'speech_recognition'

I tried to pip instal the lib but it couldn't find a version

Add detail instructions.

Add instructions for installation,
More on :

  1. how to get API's Such as Alexa and OpenAI.
  2. How to import Alexa or and openAI
  3. Better instructions on setup.

the instructions may not be clear for all.

JSONDecodeError: Expecting value: line 1 column 1

After some seconds with a lot of

ALSA lib confmisc.c:160:(snd_config_get_card) Invalid field card
ALSA lib pcm_usb_stream.c:482:(_snd_pcm_usb_stream_open) Invalid card 'card'
ALSA lib confmisc.c:160:(snd_config_get_card) Invalid field card
ALSA lib pcm_usb_stream.c:482:(_snd_pcm_usb_stream_open) Invalid card 'card'

I receive this error:

Recognized in 22.253703594207764 seconds - maybe try using a small model. See https://github.com/openai/whisper#available-models-and-languages.
Recognized:  You
Traceback (most recent call last):
  File "/home/timeu/PYTHON/chatgpt-conversation/chatgpt.py", line 21, in <module>
    resp = chatbot.get_chat_response(message)
  File "/home/timeu/.local/lib/python3.10/site-packages/revChatGPT/revChatGPT.py", line 54, in get_chat_response
    response = json.loads(response)
  File "/usr/lib/python3.10/json/__init__.py", line 346, in loads
    return _default_decoder.decode(s)
  File "/usr/lib/python3.10/json/decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
  File "/usr/lib/python3.10/json/decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

any cpu only version avalible

the nlp model selected seems need cuda to run ,any cpu only model avalible for this project, since would be easily run on embeded devices

Help required

Hey can i get your mail id or any other social media handle? Have some queries regarding one of your project

How do I install it on mac

how do i install it on mac . whats the instruction . i try to follow the instructions but when running the py file i get an error
Traceback (most recent call last):
File "/Users/aymaan/chatgpt-conversation/chatgpt.py", line 1, in
from revChatGPT.revChatGPT import Chatbot
ModuleNotFoundError: No module named 'revChatGPT.revChatGPT'

i try to install this module but i cant find it . any fix ?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.