Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

TypeError: Translations.create() got an unexpected keyword argument 'timestamp_granularities' #79

Closed
muhammed-enes-koroglu opened this issue Apr 14, 2024 · 2 comments

Comments

@muhammed-enes-koroglu
Copy link

Hi, firstly, thank you for this amazing project.

However, I have been unable to get the program running. I've tried faster-whisper first as my backend, but i kept getting some weird .dll not found errors which I could not find a solution to.

Then I uninstalled faster-whisper and installed openai using pip and manually added an environment key OPENAI_API_KEY = "sk-xxx" (xxx being the rest of my key). When i tried running, this raised an error that the api key was not defined and that I should add it to the environment or provide one in the code. Which seems weird to me, but ok. I provided one in the function call to openai and the error disappeared.

I then ran python whisper_online_server.py --host localhost --port 8089 --model large-v3 --backend openai-api, which immediately spun up the server. When I tried to go to localhost:8089, it showed on the console that there was a connection. However, even after waiting for minutes, I didn't get a website on the browser. I have tried this on multiple browsers, so I know the issue is not due to a specific browser.

Upon closing the tab, I get the following error on the console:
transcript = proc.create(**params) ^^^^^^^^^^^^^^^^^^^^^ TypeError: Translations.create() got an unexpected keyword argument 'timestamp_granularities'

After getting this error, I wanted locate where the problem laid: on the server or on the transcription software. So I ran the following command much to the same effect: python whisper_online.py audio.mp3 --model large-v3 --backend openai-api --offline

What am i doing wrong? Am I missing something?

Thank you in advance for your help!

Kind regards

@Gldkslfmsd
Copy link
Collaborator

hi,

However, even after waiting for minutes, I didn't get a website on the browser. I have tried this on multiple browsers, so I know the issue is not due to a specific browser.

there's no website. It's a TCP server, the client should send audio. You can use netcat as a client. Read the documentation in README.

@Gldkslfmsd
Copy link
Collaborator

However, I have been unable to get the program running. I've tried faster-whisper first as my backend, but i kept getting some weird .dll not found errors which I could not find a solution to.

Do you want to specify it, give reproducible details? Maybe you missed the LD_LIBRARY_PATH? https://github.com/SYSTRAN/faster-whisper?tab=readme-ov-file#install-with-pip-linux-only

Feel free to reopen if you want to continue.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants