refactor

reflector-local/0-reflector-local.py

@@ -1,10 +1,11 @@
 import os
 import subprocess
 import sys
+
 from loguru import logger
 
 # Get the input file name from the command line argument
-input_file = sys.argv[1]  
+input_file = sys.argv[1]
 # example use: python 0-reflector-local.py input.m4a agenda.txt
 
 # Get the agenda file name from the command line argument if provided
@@ -21,7 +22,7 @@ if not os.path.exists(agenda_file):
 # Check if the input file is .m4a, if so convert to .mp4
 if input_file.endswith(".m4a"):
     subprocess.run(["ffmpeg", "-i", input_file, f"{input_file}.mp4"])
-    input_file = f"{input_file}.mp4" 
+    input_file = f"{input_file}.mp4"
 
 # Run the first script to generate the transcript
 subprocess.run(["python3", "1-transcript-generator.py", input_file, f"{input_file}_transcript.txt"])
@@ -30,4 +31,4 @@ subprocess.run(["python3", "1-transcript-generator.py", input_file, f"{input_fil
 subprocess.run(["python3", "2-agenda-transcript-diff.py", agenda_file, f"{input_file}_transcript.txt"])
 
 # Run the third script to summarize the transcript
-subprocess.run(["python3", "3-transcript-summarizer.py", f"{input_file}_transcript.txt", f"{input_file}_summary.txt"])
+subprocess.run(["python3", "3-transcript-summarizer.py", f"{input_file}_transcript.txt", f"{input_file}_summary.txt"])

reflector-local/1-transcript-generator.py

@@ -1,11 +1,13 @@
 import argparse
 import os
+
 import moviepy.editor
-from loguru import logger
 import whisper
+from loguru import logger
 
 WHISPER_MODEL_SIZE = "base"
 
+
 def init_argparse() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
         usage="%(prog)s <LOCATION> <OUTPUT>",
@@ -15,6 +17,7 @@ def init_argparse() -> argparse.ArgumentParser:
     parser.add_argument("output", help="Output file path")
     return parser
 
+
 def main():
     import sys
     sys.setrecursionlimit(10000)
@@ -26,10 +29,11 @@ def main():
     logger.info(f"Processing file: {media_file}")
 
     # Check if the media file is a valid audio or video file
-    if os.path.isfile(media_file) and not media_file.endswith(('.mp3', '.wav', '.ogg', '.flac', '.mp4', '.avi', '.flv')):
+    if os.path.isfile(media_file) and not media_file.endswith(
+            ('.mp3', '.wav', '.ogg', '.flac', '.mp4', '.avi', '.flv')):
         logger.error(f"Invalid file format: {media_file}")
         return
-    
+
     # If the media file we just retrieved is an audio file then skip extraction step
     audio_filename = media_file
     logger.info(f"Found audio-only file, skipping audio extraction")
@@ -53,5 +57,6 @@ def main():
     transcript_file.write(whisper_result["text"])
     transcript_file.close()
 
+
 if __name__ == "__main__":
     main()

reflector-local/2-agenda-transcript-diff.py

@@ -1,7 +1,9 @@
 import argparse
+
 import spacy
 from loguru import logger
 
+
 # Define the paths for agenda and transcription files
 def init_argparse() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
@@ -11,6 +13,8 @@ def init_argparse() -> argparse.ArgumentParser:
     parser.add_argument("agenda", help="Location of the agenda file")
     parser.add_argument("transcription", help="Location of the transcription file")
     return parser
+
+
 args = init_argparse().parse_args()
 agenda_path = args.agenda
 transcription_path = args.transcription
@@ -19,7 +23,7 @@ transcription_path = args.transcription
 spaCy_model = "en_core_web_md"
 nlp = spacy.load(spaCy_model)
 nlp.add_pipe('sentencizer')
-logger.info("Loaded spaCy model " + spaCy_model )
+logger.info("Loaded spaCy model " + spaCy_model)
 
 # Load the agenda
 with open(agenda_path, "r") as f:

reflector-local/3-transcript-summarizer.py

@@ -1,11 +1,14 @@
 import argparse
+
 import nltk
+
 nltk.download('stopwords')
 from nltk.corpus import stopwords
 from nltk.tokenize import word_tokenize, sent_tokenize
 from heapq import nlargest
 from loguru import logger
 
+
 # Function to initialize the argument parser
 def init_argparse():
     parser = argparse.ArgumentParser(
@@ -17,12 +20,14 @@ def init_argparse():
     parser.add_argument("--num_sentences", type=int, default=5, help="Number of sentences to include in the summary")
     return parser
 
+
 # Function to read the input transcript file
 def read_transcript(file_path):
     with open(file_path, "r") as file:
         transcript = file.read()
     return transcript
 
+
 # Function to preprocess the text by removing stop words and special characters
 def preprocess_text(text):
     stop_words = set(stopwords.words('english'))
@@ -30,6 +35,7 @@ def preprocess_text(text):
     words = [w.lower() for w in words if w.isalpha() and w.lower() not in stop_words]
     return words
 
+
 # Function to score each sentence based on the frequency of its words and return the top sentences
 def summarize_text(text, num_sentences):
     # Tokenize the text into sentences
@@ -61,6 +67,7 @@ def summarize_text(text, num_sentences):
 
     return " ".join(summary)
 
+
 def main():
     # Initialize the argument parser and parse the arguments
     parser = init_argparse()
@@ -82,5 +89,6 @@ def main():
 
     logger.info("Summarization completed")
 
+
 if __name__ == "__main__":
     main()

reflector-local/whisper_summarizer_bart.py

@@ -1,15 +1,18 @@
 import argparse
 import os
 import tempfile
+
 import moviepy.editor
+import nltk
+import whisper
 from loguru import logger
 from transformers import BartTokenizer, BartForConditionalGeneration
-import whisper
-import nltk
+
 nltk.download('punkt', quiet=True)
 
 WHISPER_MODEL_SIZE = "base"
 
+
 def init_argparse() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
         usage="%(prog)s [OPTIONS] <LOCATION> <OUTPUT>",
@@ -30,6 +33,7 @@ def init_argparse() -> argparse.ArgumentParser:
 
     return parser
 
+
 # NLTK chunking function
 def chunk_text(txt, max_chunk_length=500):
     "Split text into smaller chunks."
@@ -45,6 +49,7 @@ def chunk_text(txt, max_chunk_length=500):
     chunks.append(current_chunk.strip())
     return chunks
 
+
 # BART summary function
 def summarize_chunks(chunks, tokenizer, model):
     summaries = []
@@ -56,6 +61,7 @@ def summarize_chunks(chunks, tokenizer, model):
         summaries.append(summary)
     return summaries
 
+
 def main():
     import sys
     sys.setrecursionlimit(10000)
@@ -103,7 +109,7 @@ def main():
     chunks = chunk_text(whisper_result['text'])
 
     logger.info(
-        f"Transcript broken into {len(chunks)} chunks of at most 500 words") # TODO fix variable
+        f"Transcript broken into {len(chunks)} chunks of at most 500 words")  # TODO fix variable
 
     logger.info(f"Writing summary text in {args.language} to: {args.output}")
     with open(args.output, 'w') as f:
@@ -114,5 +120,6 @@ def main():
 
     logger.info("Summarization completed")
 
+
 if __name__ == "__main__":
     main()