I was trying out the new Whisper API’s (directly from OpenAI), and used the main documentation from the OpenAI site for this example.
I got a weird internal error when I attempted to run the same on repl (after installing the required libraries).
The same code worked perfectly fine on Colab
The documentation used is here OpenAI API
File "main.py", line 3, in <module>
transcript = openai.Audio.transcribe("whisper-1", "new_file.wav")
File "/home/runner/WhisperTest/venv/lib/python3.10/site-packages/openai/api_resources/audio.py", line 55, in transcribe
requestor, files, data = cls._prepare_request(file, file.name, model, **params)
AttributeError: 'str' object has no attribute 'name'
The code I ran was
import openai
openai.api_key = “token here”
transcript = openai.Audio.transcribe(“whisper-1”, “new_file.wav”)
print (transcript)