kabanosk / whisper-website Goto Github PK

Thanks for doing this project. I'm looking for use website in a network server, but when I try to run main.py it says ti cannot import whisper module.
I tried this in my PC and found that mispell error causing this in main.py:

import whisper from whisper

I you chance second whisper to Capital letter ti works:

import whisper from Whisper

I dear, howto config in other languages?

Thanks for this, it is really useful. Can this support large-v3?

Greetings, could you please tell me if there are plans to make a full-fledged GUI that you can run as a local program?

Describe the bug
A clear and concise description of what the bug is.
For some reason, I am getting an internal server error in the content of the output file when I try to transcribe a m4a file.
OS (please complete the following information):

• [e.g. iOS]
• windows

Additional context
Add any other context about the problem here.
This is the error msg:

Hello,

I recently tried using your "website_for_whisper" repository and found it very helpful. I have a few suggestions and questions that I hope could improve the project:

GPU support: I noticed that the current implementation seems to be running the Whisper model on the CPU, which can be quite slow for some users. It would be great if the repository could be updated to support running the model on a GPU when available. This should improve the performance and make the transcription process faster.

VTT and SRT export: Another useful feature to add would be the ability to export the transcriptions in VTT and SRT formats. These formats are widely used for subtitles and captions, and having the option to export in these formats would be beneficial for many users.

Whisper 2.0: I saw that OpenAI has released Whisper 2.0, an updated version of the original Whisper model. I was wondering if the repository is using the latest version of the model. If not, could you please update the repository to use Whisper 2.0?

Thank you for your work on this project. I look forward to any updates and improvements you might make in the future.

Describe the bug
A clear and concise description of what the bug is the audio file is working ok on the browser , when the srt file download , file have a internal server error written in it

OS (please complete the following information):

• [e.g. iOS]
  Windows

Additional context
Add any other context about the problem here.

Describe the bug
The command in windows to run python is python not python3
When using Installing python from the python.org

OS (please complete the following information):
Windows

Additional context
At file: windows_run.bat
Line 3

Describe the bug

While taking input in a windows environment you get an [winerror2] file not found error : you can solve this error by making the
subprocess.Popen( ...,shell=True )
shell variable to true in _run.py file of ffpeg lib

After solving this error you get ffmpeg not found error :

you can solve this error by following this blog

and at last take the ffmpeg.exe file and copy it to the src directory to finally run the website.

OS:

• [Windows]

Additional context
Provided a method to work around the ffmpeg bug