Each response is taking around 10 seconds, maybe because I am not able to clear the Speaker Input when I press clear audio transcript.

Currently Transcribe allows use of tiny, base, small models of OpenAI.
In addition to these models OpenAI also publishes medium, large, large-v1, large-v2 models.
Location of these models is specified in https://github.com/vivekuppal/transcribe/blob/main/main.py

We can do the following

• Update Transcribe source to refer to the models at their original location
• Allow user to use medium, large, large-v1, large-v2 models using cmd line args, though give a warning that they would need powerful computers to use medium and higher models
• Delete the models from our gdrive location

This has the added benefit that we do not have to update the models regularly on our end

Hi,

I ran into an issue that I think may have been addressed in issue 101 and 84 before.

Details:

• I am using a free OpenAI account.
• I added my API key to the overide.yaml file (the key is sandwiched between single quotes)
• I am using python 3.11.7
• OS: Windows 11
• I am not using this on my main PC at the moment. I downloaded this by extracting the .zip file. I did not download the executable hosted on Google Drive.
  • Please let me know if you think using the .exe would provide data in the right window of the GUI.

Functionality

When I execute the command python main.py in my command prompt, the GUI opens successfully. The console displays the following information:
[INFO] Listening to sound from Microphone: #29 - Microphone (REDACTED)
[INFO] Adjusting for ambient noise from Default Mic. Please make some noise from the Default Mic...
[INFO] Completed ambient noise adjustment for Default Mic.
[INFO] Listening to sound from Speaker: #25 - Speakers (REDACTED) [Loopback]
[INFO] Adjusting for ambient noise from Default Speaker. Please play sound from Default Speaker...
[INFO] Completed ambient noise adjustment for Default Speaker.
[INFO] Whisper using GPU: True
READY

All things seem to start fine. The 'issue' comes when I attempt to use the application in a conversational setting. In the GUI, the window on the

• left displays a transcription (not always correctly) of what was picked up by the microphone.
• right displays "Welcome to Transcribe" at the top, and no text/response is populated. Other than the banner at the top, the window is completely blank.

After the application interprets what was picked up by the microphone, the command prompt displays the response:
Error when attempting to get a response from LLM. Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}} [INFO] Exiting gracefully..

When I view my usage details at https://platform.openai.com/usage, the balance displays $0.00. I take this to mean that generating 'responses' requires a paid account. FWIW, I am not too surprised by this.

Items of Consideration

• It may be helpful to see something in the README.md addressing response generation not displaying without a paid OpenAI/Whisper API key.
  • This is your project. I am not telling you how to run it. I just wanted to provide a way of getting ahead of this question as this project becomes more popular.
• Have you considered using other open source models?
  • When attempting to identify something that could leveraged to avoid paying for Whisper AI, I initially found https://github.com/mudler/LocalAI.
  • This may be useful https://github.com/sindresorhus/awesome-whisper.
  • I also found https://github.com/ideasman42/nerd-dictation, which uses https://github.com/alphacep/vosk-api. I am not seeing anything about pricing. There is a chance that this could be a truly 'FREE' workaround.
    • These may be helpful https://github.com/projecte-aina/oTranscribe-plus-desktop and https://github.com/oTranscribe/oTranscribe.
• Would it be possible to edit/comment on the text that is displayed in the left window of the GUI?
  • To allow users the chance to correct some of the dialogue that may not have been recorded accurately.

Currently user can enable, disable transcription from Microphone, Speaker audio using command line arguments.
Create UI to enable, disable this functionality.

Hey I just stumbled on a repo that shares similar functionalities with Transcribe. Might be worth checking it out for inspiration:
https://github.com/vocodedev/vocode-python/

Hey i tried joining the slack org using the link in the readme but looks like you can only sign in with an exisiting account. No option to register.

Currently transcription is always enabled or disabled for both Speaker, Microphone

User should have the ability to transcribe the audio from

1. Just the Speaker
2. Just the Microphone
3. Both Speaker and Microphone

Hey I see Deepgram API in parameters file.

I have added the deepgram API in override file.

But I am not able to execute it?

What command should I use?

I am not able to save my Open API key in parameters.yaml file. I get permission denied , file cannot be saved in Transcribe directory. Without using my API key, it is not answering any of the questions. I do get error message in powershell that API key is needed.

[notice] A new release of pip is available: 23.2.1 -> 23.3.1
[notice] To update, run: python.exe -m pip install --upgrade pip
PS C:\WINDOWS\system32\transcribe> python main.py
Traceback (most recent call last):
File "C:\WINDOWS\system32\transcribe\main.py", line 8, in
import yaml
ModuleNotFoundError: No module named 'yaml'
PS C:\WINDOWS\system32\transcribe>

Operating as a standalone client
[INFO] Adjusting for ambient noise from Default Mic. Please make some noise from the Default Mic...
[INFO] Completed ambient noise adjustment for Default Mic.
[INFO] Adjusting for ambient noise from Default Speaker. Please make or play some noise from the Default Speaker...
[INFO] Completed ambient noise adjustment for Default Speaker.
Using Open AI API for transcription.
READY
Traceback (most recent call last):
File "C:\Users\Saira\transcribe\main.py", line 131, in
main()
File "C:\Users\Saira\transcribe\main.py", line 121, in main
lang_combobox.configure(command=model.change_lang)
^^^^^^^^^^^^^^^^^
AttributeError: 'APIWhisperTranscriber' object has no attribute 'change_lang'

A non developer should be able to use transcribe without installing python or any of its dependencies.
One way to do it would be to use pyinstaller to create an executable for distribution

Getting this error when trying to run program

PS C:\WINDOWS\system32\transcribe> python main.py --api
Traceback (most recent call last):
File "C:\WINDOWS\system32\transcribe\main.py", line 10, in
from GPTResponder import GPTResponder
File "C:\WINDOWS\system32\transcribe\GPTResponder.py", line 5, in
import GlobalVars
File "C:\WINDOWS\system32\transcribe\GlobalVars.py", line 5, in
from audio_player import AudioPlayer
File "C:\WINDOWS\system32\transcribe\audio_player.py", line 9, in
import playsound
ModuleNotFoundError: No module named 'playsound'

The current UI does not offer the opportunity to download the conversations and save them as files.

[INFO] Listening to sound from Microphone: #24 - Microphone Array (Technologie Intel® Smart Sound)
[INFO] Listening to sound from Speaker: #22 - Enceintes (2- Realtek(R) Audio) [Loopback]
[INFO] Adjusting for ambient noise from Default Speaker. Please play sound from Default Speaker...
Traceback (most recent call last):
File "C:\Users\jin.DESKTOP-VD7S25E\transcribe\AudioRecorder.py", line 122, in adjust_for_noise
self.recorder.adjust_for_ambient_noise(self.source)
File "C:\Users\jin.DESKTOP-VD7S25E\transcribe\custom_speech_recognition_init_.py", line 437, in adjust_for_ambient_noise
assert source.stream is not None, "Audio source must be entered before adjusting, see documentation for AudioSource; are you using source outside of a with statement?"
AssertionError: Audio source must be entered before adjusting, see documentation for AudioSource; are you using source outside of a with statement?

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "main.py", line 211, in
main()
File "main.py", line 87, in main
global_vars = GlobalVars.TranscriptionGlobals()
File "C:\Users\jin.DESKTOP-VD7S25E\transcribe\GlobalVars.py", line 44, in init
self.speaker_audio_recorder = AudioRecorder.SpeakerRecorder()
File "C:\Users\jin.DESKTOP-VD7S25E\transcribe\AudioRecorder.py", line 208, in init
self.adjust_for_noise("Default Speaker",
File "C:\Users\jin.DESKTOP-VD7S25E\transcribe\AudioRecorder.py", line 122, in adjust_for_noise
self.recorder.adjust_for_ambient_noise(self.source)
File "C:\Users\jin.DESKTOP-VD7S25E\transcribe\custom_speech_recognition_init_.py", line 232, in exit
self.stream.close()
AttributeError: 'NoneType' object has no attribute 'close'

This problem occurs when opening main.py. How to solve it? Please

You exceeded your current quota, please check your plan and billing details.
string indices must be integers, not 'str'
You exceeded your current quota, please check your plan and billing details.
string indices must be integers, not 'str'
You exceeded your current quota, please check your plan and billing details.
string indices must be integers, not 'str'
You exceeded your current quota, please check your plan and billing details.
string indices must be integers, not 'str'
You exceeded your current quota, please check your plan and billing details.
string indices must be integers, not 'str'

The program is ready after that Incorrect API key error occurs

the small gdrive link is same as base model, and it leads to base model. please update it. thanks

Allow a user to provide contextual information so they can customize the responses they are getting.
E.g. A biologist participating in the conversation might want to get responses specific to certain fields of study.

I hear that Deepgram is a a more accurate, faster and cheaper ASR than Whisper. Maybe this is something worth exploring?

https://deepgram.com/

Hey, I would like to know what type of OpenAI subscription you have for those whose script works.
I upgraded my account to a Usage Tier 1 but still have the error message "You exceeded your current quota, please check your plan and billing details". Moreover, my number of api requests is still equal to 0, even though I've set the API key.

In order for GPT to remember the chat context, i have a lengthy prompt, which it reads before listening to follow up questions. This is causing it to exceed the allowed token limit. Is there anyway you can add a new function that a user can select or not select, which will automatically delete audio transcript every 10 seconds.

Could be interesting to include diarization support, so the LLM has the context of multiple speakers and which parts are spoken by who. I know deepgram already supports this in their transcription though, so maybe it's just a matter of changing up the settings on the api call and it's good to go? https://developers.deepgram.com/docs/diarization

Faster-whisper is touted to be the fastest offline STT derivative of openai whisper.
https://github.com/SYSTRAN/faster-whisper

Incorporate that into transcribe and figure if that is the best offline STT available to us.

whisper.cpp based transcription currently loads the model in memory for every iteration of the transcription.
This can be easily improved by loading the model in memory only once. Saves a lot of disk IO and will result in much better transcription speeds.

Is there any way we can save GPT responses so that we can see the history . This would help as sometimes the speaker input is so fast that GPT responses keep updating and we are not able to see all the previous responses.

Whisper.cpp is an optimized version of OpenAI whisper model written in C++.
In my tests, when using GPU whisper.cpp is 35-40% faster than OAI whisper model.

See these links
Initial issue
Discussion
Python Bindings PR

Transcribe currently only works on Windows.
Enable transcribe to work on Mac as well.

wey

Provide a command line option to allow transcription of an audio file.

Add support for multiple languages.

I have been using your Transcribe project for a project related to speech transcription. First of all, thank you for creating such a useful tool!

I have encountered an issue while trying to run the Transcribe project in my local environment. Whenever I execute the main.py script, I encounter the following error:

Traceback (most recent call last): File "main.py", line 8, in <module> from AudioTranscriber import AudioTranscriber File "D:\HelperProject\transcribe\AudioTranscriber.py", line 7, in <module> import whisper File "D:\HelperProject\transcribe\transcribeENV\lib\site-packages\whisper.py", line 69, in <module> libc = ctypes.CDLL(libc_name) File "C:\Users\Golla Prasoona\anaconda3\lib\ctypes\__init__.py", line 363, in __init__ if '/' in name or '\\' in name: TypeError: argument of type 'NoneType' is not iterable

I have tried various troubleshooting steps, such as upgrading pip, reinstalling the whisper package, and verifying the presence of whisper.py in the site-packages directory, but the issue persists.

My system environment is as follows:

Operating System: Windows 64 bit
Python Version: Python 3.8.8
Pip Version: pip 23.2.1

Getting following error after the speaker verification:

Using Open AI Whisper API for transcription.
fatal: not a git repository (or any of the parent directories): .git
Traceback (most recent call last):
File "C:\Users\Test\Desktop\transcribe-main\transcribe-main\app\transcribe\main.py", line 114, in
main()
File "C:\Users\Test\Desktop\transcribe-main\transcribe-main\app\transcribe\main.py", line 51, in main
handle_args_batch_tasks(args, global_vars)
File "C:\Users\Test\Desktop\transcribe-main\transcribe-main\app\transcribe\args.py", line 90, in handle_args_batch_tasks
interactions.params(args)
File "C:\Users\Test\Desktop\transcribe-main\transcribe-main\app\transcribe\interactions.py", line 81, in params
query_params = create_params(args)
^^^^^^^^^^^^^^^^^^^
File "C:\Users\Test\Desktop\transcribe-main\transcribe-main\app\transcribe\interactions.py", line 59, in create_params
ps = detect_ps()
^^^^^^^^^^^
File "C:\Users\Test\Desktop\transcribe-main\transcribe-main\app\transcribe\interactions.py", line 101, in detect_ps
subprocess.check_output(["powershell", "-c", "whoami"])
File "C:\Users\Test\AppData\Local\Programs\Python\Python311\Lib\subprocess.py", line 466, in check_output
return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Test\AppData\Local\Programs\Python\Python311\Lib\subprocess.py", line 548, in run
with Popen(*popenargs, **kwargs) as process:
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Test\AppData\Local\Programs\Python\Python311\Lib\subprocess.py", line 1026, in init
self._execute_child(args, executable, preexec_fn, close_fds,
File "C:\Users\Test\AppData\Local\Programs\Python\Python311\Lib\subprocess.py", line 1538, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [WinError 2] The system cannot find the file specified
Exception ignored in atexit callback: <function exit_params at 0x000001D61CB3EB60>
Traceback (most recent call last):
File "C:\Users\Test\Desktop\transcribe-main\transcribe-main\app\transcribe\interactions.py", line 111, in exit_params
query_params = create_params(args=None)
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Test\Desktop\transcribe-main\transcribe-main\app\transcribe\interactions.py", line 59, in create_params
ps = detect_ps()
^^^^^^^^^^^
File "C:\Users\Test\Desktop\transcribe-main\transcribe-main\app\transcribe\interactions.py", line 101, in detect_ps
subprocess.check_output(["powershell", "-c", "whoami"])
File "C:\Users\Test\AppData\Local\Programs\Python\Python311\Lib\subprocess.py", line 466, in check_output
return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Test\AppData\Local\Programs\Python\Python311\Lib\subprocess.py", line 548, in run
with Popen(*popenargs, **kwargs) as process:
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Test\AppData\Local\Programs\Python\Python311\Lib\subprocess.py", line 1026, in init
self._execute_child(args, executable, preexec_fn, close_fds,
File "C:\Users\Test\AppData\Local\Programs\Python\Python311\Lib\subprocess.py", line 1538, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [WinError 2] The system cannot find the file specified

I have base.pt model downloaded and trying to pass it as a parameter during execution with -m base but I'm getting:
Could not find the transcription model file: base.en.pt
Why it's trying to enforce english model?

The size of repo is big at 150Mb or so and the install seems big.
Any way we can reduce the size of two

Currently the response language of LLM can be set in the parameters.yaml.
Allow user to set the language using UI.
Users choice should be persisted across restarts of the application.

I have been running the code for around 10 minutes, and nothing has appeared. I saw some other people had the issue, but I am curious as to how long it should take. Here is my output:

[INFO] Listening to sound from Microphone: #9 - Microphone (High Definition Audio Device)
[INFO] Listening to sound from Speaker: #8 - Speakers (High Definition Audio Device) [Loopback]
[INFO] Adjusting for ambient noise from Default Speaker. Please play sound from Default Speaker...

It is stuck there, there is no error.

Add support for Deepgram API for transcription.
Some reference implementations are available at

Client Application based implementation
https://github.com/vocodedev/vocode-python/blob/2060680b4bfca961046983fe136842a5af77e151/vocode/streaming/transcriber/deepgram_transcriber.py#L126

Browser based implementation
https://deepgram.com/learn/live-transcription-mic-browser

At times it is useful to copy text. Current UI does not provide a good way to capture text and use it elsewhere.

I am interested in the project to work on adding an additional feature that could benefit the project for everyone as well

I want you to add a feature and you will be given an amount of money
Better than hiring a programmer or freelancer to do it
You are the owners of the project and you deserve it

I do not know how to contact you and I did not see contact information

executing python main.py --api takes too long to load

Any changes user makes in the UI, e.g. selection of a language are not persisted across application restarts.
Create a framework for allowing to save user changes on disk, so they are persisted across application restart.

Some users have reported that when executing transcribe with default parameters

python main.py

The microphone may not work at times.

Add a command line argument to save OpenAI key in parameters.yaml using the following syntax

python main.py -sk <OpenAI key>

All other comments, values in parameters.yaml file should stay the same as before.

This enhancement was created as a result of issue #46

Enable transcribe to work on Linux

You may not always want the audio to be recorded, so having a feature where you can stop capturing audio then start it up again would be great.

PS C:\WINDOWS\system32\transcribe> pip install -r requirements.txt
Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/cu117
Collecting numpy==1.24.3 (from -r requirements.txt (line 1))
Using cached numpy-1.24.3.tar.gz (10.9 MB)
Installing build dependencies ... done
Getting requirements to build wheel ... done
ERROR: Exception:
Traceback (most recent call last):
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\cli\base_command.py", line 180, in exc_logging_wrapper
status = run_func(*args)
^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\cli\req_command.py", line 248, in wrapper
return func(self, options, args)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\commands\install.py", line 377, in run
requirement_set = resolver.resolve(
^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\resolution\resolvelib\resolver.py", line 92, in resolve
result = self._result = resolver.resolve(
^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_vendor\resolvelib\resolvers.py", line 546, in resolve
state = resolution.resolve(requirements, max_rounds=max_rounds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_vendor\resolvelib\resolvers.py", line 397, in resolve
self._add_to_criteria(self.state.criteria, r, parent=None)
File "C:\Program Files\Python312\Lib\site-packages\pip_vendor\resolvelib\resolvers.py", line 173, in _add_to_criteria
if not criterion.candidates:
^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_vendor\resolvelib\structs.py", line 156, in bool
return bool(self._sequence)
^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\resolution\resolvelib\found_candidates.py", line 155, in bool
return any(self)
^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\resolution\resolvelib\found_candidates.py", line 143, in
return (c for c in iterator if id(c) not in self._incompatible_ids)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\resolution\resolvelib\found_candidates.py", line 47, in _iter_built
candidate = func()
^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\resolution\resolvelib\factory.py", line 206, in _make_candidate_from_link
self._link_candidate_cache[link] = LinkCandidate(
^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\resolution\resolvelib\candidates.py", line 293, in init
super().init(
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\resolution\resolvelib\candidates.py", line 156, in init
self.dist = self._prepare()
^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\resolution\resolvelib\candidates.py", line 225, in _prepare
dist = self._prepare_distribution()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\resolution\resolvelib\candidates.py", line 304, in _prepare_distribution
return preparer.prepare_linked_requirement(self._ireq, parallel_builds=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\operations\prepare.py", line 538, in prepare_linked_requirement
return self._prepare_linked_requirement(req, parallel_builds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\operations\prepare.py", line 653, in _prepare_linked_requirement
dist = _get_prepared_distribution(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\operations\prepare.py", line 69, in _get_prepared_distribution
abstract_dist.prepare_distribution_metadata(
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\distributions\sdist.py", line 48, in prepare_distribution_metadata
self._install_build_reqs(finder)
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\distributions\sdist.py", line 118, in _install_build_reqs
build_reqs = self._get_build_requires_wheel()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\distributions\sdist.py", line 95, in _get_build_requires_wheel
return backend.get_requires_for_build_wheel()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_internal\utils\misc.py", line 697, in get_requires_for_build_wheel
return super().get_requires_for_build_wheel(config_settings=cs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_vendor\pyproject_hooks_impl.py", line 166, in get_requires_for_build_wheel
return self._call_hook('get_requires_for_build_wheel', {
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\site-packages\pip_vendor\pyproject_hooks_impl.py", line 321, in _call_hook
raise BackendUnavailable(data.get('traceback', ''))
pip._vendor.pyproject_hooks._impl.BackendUnavailable: Traceback (most recent call last):
File "C:\Program Files\Python312\Lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 77, in build_backend
obj = import_module(mod_path)
^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\importlib_init.py", line 90, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "", line 1381, in _gcd_import
File "", line 1354, in _find_and_load
File "", line 1304, in _find_and_load_unlocked
File "", line 488, in _call_with_frames_removed
File "", line 1381, in _gcd_import
File "", line 1354, in _find_and_load
File "", line 1325, in _find_and_load_unlocked
File "", line 929, in _load_unlocked
File "", line 994, in exec_module
File "", line 488, in call_with_frames_removed
File "C:\Users\suao1\AppData\Local\Temp\pip-build-env-6rc03cez\overlay\Lib\site-packages\setuptools_init.py", line 10, in
import distutils.core
ModuleNotFoundError: No module named 'distutils'