Fourth part of the NLP analysis for the Medium article on AWS ML/AI tools for NLP.

nlp_aws_medium_part4.py

# 15) Iterate over the speakers and apply spaCy visualizer on each speech
for index, row in df_audio.iterrows():
    print(f"Rendering {index}'s texts")    
    nlp = spacy.load('en_core_web_lg')
    original_transcription = nlp(original_transcriptions.get(index))    
    transcribe_transcription = nlp(get_text_from_json(bucket_name, row.json_transcription))
    
    svg_original = spacy.displacy.render(original_transcription, style="ent",jupyter=False)
    svg_transcribe = spacy.displacy.render(transcribe_transcription, style="ent",jupyter=False)
    
    with open(f'{index}_original.html', 'w',  encoding="utf-8") as page:
        page.write(svg_original)
    with open(f'{index}_transcribe.html', 'w',  encoding="utf-8") as page:
        page.write(svg_transcribe)