Using OpenAI API to get transcripts of local videos

Question

I am trying to write code to get the transcripts out of some video files I downloaded. So far I got the following:

def save_audio_transcripts(video_files):
    for video_file in video_files:
        # This is the code to load a local video file and parse audio
        # Transform the downloaded file in "wav"
        output_audio_file = os.path.splitext(video_file)[0] + ".wav"
        extract_audio(video_file, output_audio_file)
        
        #This is the code to load a YouTube Video and save the audio locally
        loader = GenericLoader(
            output_audio_file,
            OpenAIWhisperParser()
        )
    
        #This is the code to transcribe the audio into text and save it a file
        docs = loader.load()
        output_directory = os.path.dirname(video_file)
        output_transcript = output_directory + '/transcripts_' + os.path.splitext(os.path.basename(video_file))[0] + '.txt' 
        
        with open(output_transcript, 'w', encoding='utf-8') as f:
        #with open(savedir+"/"+transcriptfile, 'w', encoding='latin-1') as f:
            for item in docs:
                # write each item
                f.write(item.page_content)
            print('Done')
        
    return docs

where extract_audio is a function that creates a .wav file out of the .mp4 video file.

However, from

docs = loader.load()

I get the following error:

File ~\anaconda3\lib\site-packages\langchain\document_loaders\generic.py:85 in lazy_load for blob in self.blob_loader.yield_blobs():

AttributeError: 'str' object has no attribute 'yield_blobs'

Can I please get some help?