dougdouggithub / babagaboosh Goto Github PK

On a fresh setup, you are still missing the azure.cognitiveservices module as also pointed out here.

According to that post you need pip install azure-cognitiveservices-speech as well in the requirements.

However, upon installing that, I get a module missing error with pydantic_core, which can also be installed with pip install pydantic, although it doesn't seem to have helped.

Your video about me was a PERSONAL ATTACK and I want it taken down as soon as possible. I will mark this issue as complete after submitting. You better take it down before I take you down.

With love, Jake

You should disable Issues for this repository so you're not bombarded with troll messages in your issues.

Please remove all references to Doug having hair in the project

Understandable if nobody can get to this.

I've been attempting to get this running inside a Docker container on a MacOS host, and continue to run into blockers in regards to the container finding an audio device on the host. I've attempted to configure Pulseaudio for this purpose, but have come up with little success.

If anyone has gotten this running in such an environment, I would greatly appreciate the addition of instructions in the ReadMe. Dockerfile and docker-compose.yml would be a huge plus, though I am pretty certain I can set those up.

Now your requirements.txt gives this error:

ERROR: Could not find a version that satisfies the requirement azure-cognitiveservices-speech==12.19.0 (from versions: 1.24.0, 1.24.1, 1.24.2, 1.25.0, 1.25.1b1, 1.26.0, 1.27.0, 1.28.0, 1.29.0, 1.30.0, 1.31.0, 1.32.1, 1.33.0, 1.34.0)
ERROR: No matching distribution found for azure-cognitiveservices-speech==12.19.0

Fairly self-explanatory!

Bug description: Code does not feature chair enough.

Repro steps: Watch dougdoug stream.

im proud

On the Humongous Entertainment's Terms and Conditions, quote:

Images are either the property of, or used with permission by, Humongous Entertainment. The use of these images by you, or anyone else authorized by you, is prohibited unless specifically permitted by these Terms and Conditions. Any unauthorized use of the images may violate copyright laws, trademark laws, the laws of privacy and publicity, and communications regulations and statutes.

Through GitHub's DMCA Takedown Policy, they can file a report due to the repo using an image of Pajama Sam.
GitHub won't disable the entire repo when they attempt this, as it is only a single file. However, they only give 1 business day for the repo owner to delete the file from the repository and remedy the situation. If the content is not removed by then, GitHub will disable access to the repository.

I recommend removing the infringing content (or replacing it with a well-known public-domain character with mouse ears and a steamboat hat) before the copyright owners choose to send a DMCA takedown.
Although, an ye harm none, do as ye will.

It so happens that

I no no wanna :'(

Need more baba, doug

You seem to have not followed the Rust Style Guide, please fix

just ask chatGPT to improve it lol

If you are getting the following error:

pip install azure-storage
Defaulting to user installation because normal site-packages is not writeable
Collecting azure-storage
Using cached azure-storage-0.37.0.zip (4.3 kB)
Preparing metadata (setup.py) ... error
error: subprocess-exited-with-error

× python setup.py egg_info did not run successfully.
│ exit code: 1
╰─> [20 lines of output]
Traceback (most recent call last):
File "", line 2, in
File "", line 34, in
File "C:\Users****\AppData\Local\Temp\pip-install-sygw9hnm\azure-storage_7f36e5eeaf72445ea4bf307ccce5f4c9\setup.py", line 55, in
raise RuntimeError(message)
RuntimeError:

  Starting with v0.37.0, the 'azure-storage' meta-package is deprecated and cannot be installed anymore.
  Please install the service specific packages prefixed by `azure` needed for your application.
 
  The complete list of available packages can be found at:
  https://aka.ms/azsdk/python/all
 
  Here's a non-exhaustive list of common packages:
 
  - [azure-storage-blob](https://pypi.org/project/azure-storage-blob) : Blob storage client
  - [azure-storage-file-share](https://pypi.org/project/azure-storage-file-share) : Storage file share client
  - [azure-storage-file-datalake](https://pypi.org/project/azure-storage-file-datalake) : ADLS Gen2 client
 
  [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed

× Encountered error while generating package metadata.
╰─> See above for output.

note: This is an issue with the package mentioned above, not pip.
hint: See above for details.

USE: pip install azure-storage-blob

For some reason, this program works perfectly for me the first time around, but on the second loop (after 1 GPT response is spoken), the Speech-To-Text fails and always returns a blank string no matter what I say.
This happens with both the speechtotext_from_mic and speechtotext_from_mic_continuous functions
This also happens when running azure_speech_to_text.py in isolation.

Running using VScode console in Win11

getting this- i have done everything from the fixes but keep getting this even under a fresh install

Exception has occurred: PydanticUserError
If you use @root_validator with pre=False (the default) you MUST specify skip_on_failure=True. Note that @root_validator is deprecated and should be replaced with @model_validator.

For further information visit https://errors.pydantic.dev/2.5/u/root-validator-pre-skip
File "C:\Users***\Desktop\Babagaboosh-main\eleven_labs.py", line 1, in
from elevenlabs import generate, stream, set_api_key, voices, play, save
File "C:\Users*****\Desktop\Babagaboosh-main\chatgpt_character.py", line 6, in
from eleven_labs import ElevenLabsManager
pydantic.errors.PydanticUserError: If you use @root_validator with pre=False (the default) you MUST specify skip_on_failure=True. Note that @root_validator is deprecated and should be replaced with @model_validator.

For further information visit https://errors.pydantic.dev/2.5/u/root-validator-pre-skip

Once upon a time, in a quaint little village nestled between rolling hills and whispering woods, lived a young boy named Doug Doug. He was known for his bright red hair, a mischievous smile, and a heart full of adventure. The villagers loved Doug Doug for his kind nature and his eagerness to help anyone in need.

But beyond the safe confines of the village, in the deepest, darkest part of the woods, lived the infamous witch Babagaboosh. She was as old as the hills and as cunning as a fox. With her crooked nose, icy blue eyes, and a cackle that could chill your bones, Babagaboosh was feared by all.

One sunny morning, Doug Doug was playing near the edge of the woods when he heard a faint cry for help. Guided by his brave heart, he ventured into the forest, unaware of the dangers that lay ahead. As he delved deeper, the trees grew taller, and the light dimmer, until he found himself in the heart of Babagaboosh’s domain.

There, trapped in a cage, was a beautiful golden bird, singing a melancholic tune. Doug Doug knew he had to free the bird, but as he approached the cage, Babagaboosh appeared in a puff of green smoke.

"Who dares enter my forest?" she screeched, her voice echoing through the trees.

"It’s just me, Doug Doug. I want to free the bird," he said, trying to hide his fear.

Babagaboosh cackled. "You? A mere child? This bird is my prized possession. But I'll make you a deal. If you can complete three challenges, the bird is yours. Fail, and you'll become a frog forever!"

Doug Doug, with a determined nod, accepted her challenge.

The first challenge was to find the rare blue rose that bloomed only at midnight. With patience and determination, Doug Doug waited until the stroke of midnight and plucked the elusive flower under the moonlit sky.

The second challenge was to fetch a vial of water from the Crystal Lake, guarded by mischievous sprites. Using his wit, Doug Doug tricked the sprites into a game of riddles and secured the vial of water.

The final challenge was the toughest. Babagaboosh asked Doug Doug to retrieve a lock of hair from the sleeping Giant of the North. With stealth and courage, Doug Doug climbed the giant’s towering bed and snipped a lock of hair.

Impressed and defeated, Babagaboosh kept her word. She released the golden bird, which transformed into a beautiful fairy, the guardian of the forest. In gratitude, the fairy granted Doug Doug a wish. He wished for peace between the village and the forest.

From that day on, the villagers and the creatures of the forest lived in harmony. Babagaboosh, softened by Doug Doug’s bravery and kindness, became less feared and more respected. And Doug Doug? He became a legend, the brave boy who outwitted the evil witch Babagaboosh and brought unity to his world.

I don't like your malware

Really expected more from you Doug

I am not good at computr

huge problem, please fix

i know Python too please DougDoug i know Discord.py we could make something beautiful

Line 19 of elevenlabs.py is being highlighted with this error after submitting voice inputs:

Exception has occurred: TypeError
list indices must be integers or slices, not str
File "C:\Users---\Babagaboosh-main\eleven_labs.py", line 19, in text_to_audio
audio_saved = generate(
File "C:\Users---\Babagaboosh-main\chatgpt_character.py", line 62, in
elevenlabs_output = elevenlabs_manager.text_to_audio(openai_result, ELEVENLABS_VOICE, False)
TypeError: list indices must be integers or slices, not str

Really gave learning python my best shot for the sake of this cool project and managed to make it pretty far but after about 3 hours I have to admit defeat and ask if anyone knows a fix for this

So got everything working but when it goes to translate what chat GPT said it comes up with this error

Exception has occurred: ValueError
Voice 'Pointboat' not found.
File "C:\Users*****\Desktop\Babagaboosh-main\eleven_labs.py", line 19, in text_to_audio
audio_saved = generate(
File "C:\Users***\Desktop\Babagaboosh-main\chatgpt_character.py", line 62, in
elevenlabs_output = elevenlabs_manager.text_to_audio(openai_result, "Pointboat", False)
ValueError: Voice 'Pointboat' not found.

For example, your OBS Websockets code that is shared across your projects should be in its own repository, so that if you make later changes, you don't have to copy those changes to every git repository.

I mean, the author is already bald, but I feel like it’s not enough. Please fix, THX <3

As you can see in my console it recognized me say "Hello this is a test.", but did not send an AI response and instead said that it did not receive any input, can anyone help?

First time github user here.
I troubleshooted most of my issues with Doug's code and my system.

I am now at the final stretch and am suffering 1 of 3 issues:

1. stt(speech to text) is not properly being sent to chatgpt meaning gpt doesn't have anything to work with -> a response of NONE

2)The response is recorded but doesn't get properly sent to the API(wrong variable name?)

3)The response is being sent to GPT, GPT responds but the text is not saved or set to a variable

All of this is based roughly off of Doug's original code. I will provide code when available - currently running to a hockey game!

When using this with gpt-3.5, the code spits out a ton of errors.
Here they are:
(I tried changing things in the openai_chat.py file and nothing worked)

Traceback (most recent call last):
  File "/Users/Joshua/Documents/Other/coding/Babagaboosh-main/chatgpt_character.py", line 59, in <module>
    openai_result = openai_manager.chat_with_history(mic_result)
  File "/Users/Joshua/Documents/Other/coding/Babagaboosh-main/openai_chat.py", line 74, in chat_with_history
    completion = self.client.chat.completions.create(
  File "/Users/Joshua/Documents/Other/coding/Babagaboosh-main/.venv/lib/python3.9/site-packages/openai/_utils/_utils.py", line 271, in wrapper
    return func(*args, **kwargs)
  File "/Users/Joshua/Documents/Other/coding/Babagaboosh-main/.venv/lib/python3.9/site-packages/openai/resources/chat/completions.py", line 643, in create
    return self._post(
  File "/Users/Joshua/Documents/Other/coding/Babagaboosh-main/.venv/lib/python3.9/site-packages/openai/_base_client.py", line 1112, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
  File "/Users/Joshua/Documents/Other/coding/Babagaboosh-main/.venv/lib/python3.9/site-packages/openai/_base_client.py", line 859, in request
    return self._request(
  File "/Users/Joshua/Documents/Other/coding/Babagaboosh-main/.venv/lib/python3.9/site-packages/openai/_base_client.py", line 949, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: Error code: 404 - {'error': {'message': 'The model `gpt-4` does not exist or you do not have access to it. Learn more: https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4.', 'type': 'invalid_request_error', 'param': None, 'code': 'model_not_found'}}
(.venv) Joshua@Matthew's MacBook Pro Babagaboosh-main % 

we need darkness stream
where darkness tries to find pajama sam

Here is what happens:
CLOSING speech recognition on SpeechRecognitionCanceledEventArgs(session_id=a7c4bbcbe3714869b19b636cbd8ed2c3, result=SpeechRecognitionResult(result_id=5e6c08f125544f29b008796a77ccb583, text="", reason=ResultReason.Canceled))
CLOSING speech recognition on SessionEventArgs(session_id=a7c4bbcbe3714869b19b636cbd8ed2c3)

can anyone help?

This is how best to make python virtual environment in VScode https://code.visualstudio.com/docs/python/environments
make sure to have Python 3.9.2 installed before following these steps. It does not need to be in the path just installed and you can select it has the python for it.

And it's still looking at me. Babagaboosh!!!

Babagaboosh!?

generate is no longer importable from elevenlabs so the entire eleven_labs.py file need to be updated, also a lot of other things out of date

have tried to fix it myself but havent had any luck so far