Recognize only first row

[mixer123]

This code recognize only one row . Why ?

import whisper

model = whisper.load_model("base")

# load audio and pad/trim it to fit 30 seconds
audio = whisper.load_audio("abba.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(fp16 = False)
result = whisper.decode(model, mel, options)

# print the recognized text
print(result.text)

[ryanheise]

If you mean that it is not transcribing more than 30 seconds, that is what whisper.decode() does, which is why you have trimmed it to 30 seconds to fit the maximum that the model can process at once.

Instead of doing that, you can use the higher level model.transcribe() which will loop over the entire file in 30 second chunks and stitch them together. For example:

audio = "abba.mp3"  # or you could use load_audio
result = model.transcribe(audio)