How i can fix these errors please

[norbvk]

Hello, I have a problem so I hope some programmers can help me solve it.

Basically I run this :

import whisper model = whisper.load_model("base") result = model.transcribe('test.mp3', fp16=False)

And I get this:

---

Output exceeds the size limit. Open the full output data in a text editor.

Error Traceback (most recent call last)
File
38 try:
39 # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
40 # Requires the ffmpeg CLI and ffmpeg-python package to be installed.
41 out, _ = (
---> 42 ffmpeg.input(file, threads=0)
43 .output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=sr)
44 .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
45 )
46 except ffmpeg.Error as e:
File
324 if retcode:
--> 325 raise Error('ffmpeg', out, err)
326 return out, err

Error: ffmpeg error (see stderr output for detail)

The above exception was the direct cause of the following exception:

RuntimeError Traceback (most recent call last)
Cell In[25], line 4
1 import whisper
...
libswscale 6. 7.100 / 6. 7.100
libswresample 4. 7.100 / 4. 7.100
libpostproc 56. 6.100 / 56. 6.100
test.mp3: No such file or directory

---

My goal is just to transcribe an mp3 audio file "test.mp3" into text, via the AI Whisper of OpenAI.

And honestly, I've been at it for two days now and I'm not getting anywhere, I've opened the files in question, located lines 42 and 325 but I don't know what to do next.

Thank you in advance for your help and your explanations.

[FurkanGozukara]

I have a video that explains how to use whisper it may help

https://www.youtube.com/watch?v=msj3wuYf3d8

[pwyhack]

I am also having the same issue, has anyone figured it out? On windows 11

[FurkanGozukara]

I am also having the same issue, has anyone figured it out? On windows 11

Join our discord and I can try to help via anydesk

But first watch video and see if it works

[jongwook]

It appears that test.mp3 is not in the same directory that you are running the whisper command. You can check if it is in the same directory by running dir test.mp3 (Windows) or ls test.mp3 (MacOS or Linux).

[Jmiguel14]

You must install the package that it showed there ffmpeg. Here the setup doc of whisper: https://github.com/openai/whisper#setup that shows you how to install it depending on your OS.

[asimawan65]

OS: Windows 11
Installed components:

1. Python 3.10.10
2. PyTorch v 2.0.1
3. Chocolatey v2.2.0
4. FFmpeg Packages v6.0.0
5. openai-whisper-20230314.

[ahsannawazch]

Facing the same error. You got any fix?

[freerider7777]

same problem, any solution?

[freerider7777]

whisper errors solved by using Ubuntu in WSL on Windows :) Works fine

[BienPinche]

any solution for windows yet?

[Muthukrishnan1902]

Hey i need to use openai whisper model for transcibe the audio , and i have a condition like without installing ffmpeg and openai API . is is possible with hardcode ? if yes how to proceed with it?

[ryanheise]

I suggest posting a new question in a new discussion.