module 'torchaudio' has no attribute 'list_audio_backends'

[Mohad009]

I’m getting an error when running the transcription. I followed exactly what you did in the notebook you provided. I tried uninstalling and reinstalling different package versions where the attribute exists, but that only created more conflicts with other dependencies. What should I do to fix this?

from speechlib import Transcriptor
file = "/content/drive/MyDrive/Colab Notebooks/0ackyKbNcd8.wav"  # your audio file
voices_folder = "/content/drive/MyDrive/Colab Notebooks/voices" # voices folder containing voice samples for recognition
language = "ar"          # language code
log_folder = "/content/drive/MyDrive/Colab Notebooks/logs"      # log folder for storing transcripts
modelSize = "large-v3"     # size of model to be used [tiny, small, medium, large-v1, large-v2, large-v3]
quantization = False   # setting this 'True' may speed up the process but lower the accuracy
ACCESS_TOKEN = "*****" # get permission to access pyannote/speaker-diarization@2.1 on huggingface
# os.makedirs(log_folder,exist_ok=True)
# quantization only works on faster-whisper
transcriptor = Transcriptor(file, log_folder, language, modelSize, ACCESS_TOKEN, voices_folder, quantization)


# use faster-whisper (simply faster)
print("running faster-whisper....")
res = transcriptor.faster_whisper()

AttributeError: module 'torchaudio' has no attribute 'list_audio_backends'