Option to skip silence for whisper.pad_or_trim

[rickif]

import whisper

model = whisper.load_model("turbo")

# 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, n_mels=model.dims.n_mels).to(model.device)

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

I am using an example to detect the language of an audio file. If the audio begins with a silence longer than 30 seconds, the performance of the detection will be poor, and the confidence level will be low. I wonder if adding an offset option to whisper.pad_or_trim would be helpful. This way, we could skip the silent portion if the detection confidence is low.