Giter VIP home page Giter VIP logo

porcupinepipeline's Issues

Other languages support

For other language support, it would be useful to support the --keyword-paths and --model-path arguments as Environment Variables. And linking Volumes with these files.

Each container consumes Picovoice MAU

While troubleshooting audio in my container, I ran into a Picovoice error:

AccessKey *** has reached it's [sic] temporary device limit

It looks like each execution counts as a unique user to Picovoice, so I have to wait a month until trying again. Would this be worth mentioning in the readme?

Open Ai functions integration

This might be beyond the scope of this project but integrating this with open AI functions could make this very powerful. It could also provide a way to interface with home assistant devices.

ConnectionResetError

Hi!

I get a ConnectionResetError: Cannot write to closing transport error message when I pronounce the wake word and approximately 1 minute of inactivity elapsed after the last tts response was received. I believe this is because of the websocket has been closed.

I am using windows 11. Here is the stacktrace:

2023-07-20 23:51:01,355  INFO Waiting for wake word to trigger audio
2023-07-20 23:52:44,837  INFO Detected keyword `alexa`
2023-07-20 23:52:45,016  INFO Listening and sending audio to voice pipeline
Traceback (most recent call last):
  File "c:\Users\User\projects\PorcupinePipeline-main\voice_pipeline.py", line 489, in <module>
    asyncio.run(main())
  File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\asyncio\runners.py", line 190, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\asyncio\runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\asyncio\base_events.py", line 653, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "c:\Users\User\projects\PorcupinePipeline-main\voice_pipeline.py", line 136, in main
    await loop_pipeline(state)
  File "c:\Users\User\projects\PorcupinePipeline-main\voice_pipeline.py", line 236, in loop_pipeline
    await websocket.send_json(pipeline_args)
  File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\aiohttp\client_ws.py", line 165, in send_json
    await self.send_str(dumps(data), compress=compress)
  File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\aiohttp\client_ws.py", line 151, in send_str
    await self._writer.send(data, binary=False, compress=compress)
  File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\aiohttp\http_websocket.py", line 690, in send
    await self._send_frame(message, WSMsgType.TEXT, compress)
  File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\aiohttp\http_websocket.py", line 646, in _send_frame
    self._write(header + mask + message)
  File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\aiohttp\http_websocket.py", line 663, in _write
    raise ConnectionResetError("Cannot write to closing transport")
ConnectionResetError: Cannot write to closing transport

Feat: Home Assistant Assist pipeline called first

I think this idea would be really cool, but if it isn't inline with the direction of this project, then I can close this and work on a personal fork.

Idea: The initial pipeline could be the Assist pipeline, then if the response is Sorry, I couldn't understand that then you could call a second OpenAI pipeline that could handle the input. Calling the Home assistant Assist pipeline first would allow actions to be executed, but still also have the ability to converse in natural language with ChatGPT. One way to enhance the performance is to have the first pipeline only be STT and Assist and the second pipeline only ChatGPT and TTS.

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.