Customizable language option

[tiagojulianoferreira]

Hello!

I believe the app is set to automatically translate to English, would it make sense to leave this option customizable via the frontend?

[XamHans]

Hi, indeed that would be cool. I just found how to achieve with with the help of the CLI. Do you have more info about this how to achieve this in code?

[tiagojulianoferreira]

In fact, I noticed that by simply changing the model_name variable directly in the code to "base" in the line below, the app already transcribed my test video in the original language (Portuguese).
https://github.com/XamHans/video-2-text/blob/master/webserver/businessLogic.py#L14

By default, whisper detects the language of the video, but I couldn't understand why it translated a video in Portuguese into English using the original code.

[XamHans]

I dont know either. You can try this approach provided by original whisper repo:
Below is an example usage of whisper.detect_language() and whisper.decode() which provide lower-level access to the model.

import whisper

model = whisper.load_model("base")

# load audio and pad/trim it to fit 30 seconds
audio = whisper.load_audio("audio.mp3")
audio = whisper.pad_or_trim(audio)

# make log-Mel spectrogram and move to the same device as the model
mel = whisper.log_mel_spectrogram(audio).to(model.device)

# detect the spoken language
_, probs = model.detect_language(mel)
print(f"Detected language: {max(probs, key=probs.get)}")

# decode the audio
options = whisper.DecodingOptions()
result = whisper.decode(model, mel, options)

# print the recognized text
print(result.text)