huwprosser / carter-voice-assistant

An example project showing how to use www.carterapi.com as a voice assistant.

I am Huw.

Contrary to Popular Belief, I Know Exactly What I'm Doing.

I've been helping A.I take over since 2008.

• 🙈 In a three-way relationship with Co-Pilot and ChatGPT

• 🤖 Building incredible AI characters at Carter.chat

• 🔨 "You may know me as the guy building JARVIS from Iron Man IRL on TikTok" 80m+ views, 1m+ followers

Here are some open source things I built for you.

• Whisper (ASR) in the browser
• Face Recognition
• Image Clustering
• ChatGPT Desktop

Build something cool.

carter-voice-assistant's Issues

You cant delete agents

Carter Api Problem

Hello I'm Facing A Problem While Trying to Launch Carter. I am on windows and I uninstall and reinstall everything but still same issue and I'm using anaconda prompt for new environment

Issue:
Carter Voice Client Starting...
Loading voice models. This may take a second...
Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at facebook/wav2vec2-base-960h and are newly initialized: ['wav2vec2.masked_spec_embed']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
done
Listening...
2022-09-11 22:29:20.333647: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2022-09-11 22:29:20.333750: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
expected scalar type Double but found Float

FileNotFoundError: [WinError 2] The system cannot find the file specified

I'm getting this error when running app.py

Hello there! I'm Jarvis, a personal AI assistant. How may I assist you today? Traceback (most recent call last): File "C:\Users\dmerg\Documents\Projects\JARVIS\carter_project\app.py", line 170, in <module> jc = CarterClient( ^^^^^^^^^^^^^ File "C:\Users\dmerg\Documents\Projects\JARVIS\carter_project\app.py", line 41, in __init__ self.getOpener() ^^^^^^^^^^^^^^^^ File "C:\Users\dmerg\Documents\Projects\JARVIS\carter_project\app.py", line 154, in getOpener self.playAudio(output['audio']) File "C:\Users\dmerg\Documents\Projects\JARVIS\carter_project\app.py", line 101, in playAudio audio_data = AudioSegment.from_file(BytesIO(r.content)).export(format='wav') ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\dmerg\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\pydub\audio_segment.py", line 728, in from_file info = mediainfo_json(orig_file, read_ahead_limit=read_ahead_limit) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\dmerg\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\pydub\utils.py", line 274, in mediainfo_json res = Popen(command, stdin=stdin_parameter, stdout=PIPE, stderr=PIPE) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.11_3.11.1008.0_x64__qbz5n2kfra8p0\Lib\subprocess.py", line 1024, in __init__ self._execute_child(args, executable, preexec_fn, close_fds, File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.11_3.11.1008.0_x64__qbz5n2kfra8p0\Lib\subprocess.py", line 1509, in _execute_child hp, ht, pid, tid = _winapi.CreateProcess(executable, args, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ FileNotFoundError: [WinError 2] The system cannot find the file specified
Not sure where to start debugging on this? any insights?

Not listening

When I run app.py on my laptop. it does all of the startup but after listeining it doesnt listen at all and doesnt come up with any error.

'output' error

hi so i was working and trying to install this when i got this error.

Traceback (most recent call last): File "C:\Users\(name)\Downloads\carter-voice-assistant-main\carter-voice-assistant-main\app.py", line 170, in <module> jc = CarterClient( ^^^^^^^^^^^^^ File "C:\Users\(name)\Downloads\carter-voice-assistant-main\carter-voice-assistant-main\app.py", line 41, in __init__ self.getOpener() ^^^^^^^^^^^^^^^^ File "C:\Users\(name)\Downloads\carter-voice-assistant-main\carter-voice-assistant-main\app.py", line 148, in getOpener output = agent_response['output'] ~~~~~~~~~~~~~~^^^^^^^^^^ KeyError: 'output'

can anyone help me with this?

thx

expected scalar type Double but found Float

OS: Windows
py version: 3.10.4 running in a venv

After "Listening..." is prompted and something has been said I get the response.
"expected scalar type Double but found Float"

*Invoking app.py*
Carter Voice Client Starting...
Loading voice models. This may take a second...
Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at facebook/wav2vec2-base-960h and are newly initialized: ['wav2vec2.masked_spec_embed']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
done
Listening...
expected scalar type Double but found Float