INNER CODE UNIT · Python

process_chapter_files

DrewThomasson/VoxNovel · 2GPU_Audio_generation.py:191

    def process_chapter_files(folder_path, output_csv):
        with open(output_csv, 'w', newline='', encoding='utf-8') as csvfile:
            writer = csv.writer(csvfile)
            # Write the header row
            writer.writerow(['Text', 'Start Location', 'End Location', 'Is Quote', 'Speaker', 'Chapter'])

            # Process each chapter file
            chapter_files = sorted(os.listdir(folder_path), key=lambda x: int(x.split('_')[1].split('.')[0]))
            for filename in chapter_files:
                if filename.startswith('chapter_') and filename.endswith('.txt'):
                    chapter_number = int(filename.split('_')[1].split('.')[0])
                    file_path = os.path.join(folder_path, filename)

                    try:
                        with open(file_path, 'r', encoding='utf-8') as file:
                            text = file.read()
                            sentences = nltk.tokenize.sent_tokenize(text)
                            for sentence in sentences:

View source record →