refactor

client.py

@@ -1,12 +1,14 @@
 import argparse
 import asyncio
 import signal
+from utils.log_utils import logger
 
 from aiortc.contrib.signaling import (add_signaling_arguments,
                                       create_signaling)
 
 from stream_client import StreamClient
 
+
 async def main():
     parser = argparse.ArgumentParser(description="Data channels ping/pong")
 
@@ -35,17 +37,17 @@ async def main():
 
     async def shutdown(signal, loop):
         """Cleanup tasks tied to the service's shutdown."""
-        logging.info(f"Received exit signal {signal.name}...")
+        logger.info(f"Received exit signal {signal.name}...")
-        logging.info("Closing database connections")
+        logger.info("Closing database connections")
-        logging.info("Nacking outstanding messages")
+        logger.info("Nacking outstanding messages")
         tasks = [t for t in asyncio.all_tasks() if t is not
                  asyncio.current_task()]
 
         [task.cancel() for task in tasks]
 
-        logging.info(f"Cancelling {len(tasks)} outstanding tasks")
+        logger.info(f"Cancelling {len(tasks)} outstanding tasks")
         await asyncio.gather(*tasks, return_exceptions=True)
-        logging.info(f"Flushing metrics")
+        logger.info(f"Flushing metrics")
         loop.stop()
 
     signals = (signal.SIGHUP, signal.SIGTERM, signal.SIGINT)

reflector-local/0-reflector-local.py

@@ -1,6 +1,7 @@
 import os
 import subprocess
 import sys
+
 from loguru import logger
 
 # Get the input file name from the command line argument

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)
@@ -26,7 +29,8 @@ 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
 
@@ -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

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)
@@ -114,5 +120,6 @@ def main():
 
     logger.info("Summarization completed")
 
+
 if __name__ == "__main__":
     main()

server_executor_cleaned.py

@@ -2,7 +2,6 @@ import asyncio
 import datetime
 import io
 import json
-from loguru import logger
 import sys
 import uuid
 import wave
@@ -13,6 +12,7 @@ from aiohttp import web
 from aiortc import MediaStreamTrack, RTCPeerConnection, RTCSessionDescription
 from aiortc.contrib.media import MediaRelay
 from av import AudioFifo
+from loguru import logger
 from whisper_jax import FlaxWhisperPipline
 
 from utils.server_utils import run_in_executor
@@ -23,7 +23,9 @@ pcs = set()
 relay = MediaRelay()
 data_channel = None
 total_bytes_handled = 0
-pipeline = FlaxWhisperPipline("openai/whisper-tiny", dtype=jnp.float16, batch_size=16)
+pipeline = FlaxWhisperPipline("openai/whisper-tiny",
+                              dtype=jnp.float16,
+                              batch_size=16)
 
 CHANNELS = 2
 RATE = 48000
@@ -50,18 +52,6 @@ def channel_send(channel, message):
 
 
 def get_transcription(frames):
-    print("Transcribing..")
-    # samples = np.ndarray(
-    #     np.concatenate([f.to_ndarray() for f in frames], axis=None),
-    #     dtype=np.float32,
-    # )
-    # whisper_result = pipeline(
-    #     {
-    #         "array": samples,
-    #         "sampling_rate": 48000,
-    #     },
-    #     return_timestamps=True,
-    # )
     out_file = io.BytesIO()
     wf = wave.open(out_file, "wb")
     wf.setnchannels(CHANNELS)
@@ -108,7 +98,6 @@ class AudioStreamTrack(MediaStreamTrack):
 
 async def offer(request):
     params = await request.json()
-    print("Request received")
     offer = RTCSessionDescription(sdp=params["sdp"], type=params["type"])
 
     pc = RTCPeerConnection()
@@ -132,7 +121,6 @@ async def offer(request):
             channel_log(channel, "<", message)
 
             if isinstance(message, str) and message.startswith("ping"):
-                # reply
                 channel_send(channel, "pong" + message[4:])
 
     @pc.on("connectionstatechange")
@@ -144,19 +132,13 @@ async def offer(request):
 
     @pc.on("track")
     def on_track(track):
-        print("Track %s received" % track.kind)
         log_info("Track %s received", track.kind)
-        # Trials to listen to the correct track
         pc.addTrack(AudioStreamTrack(relay.subscribe(track)))
-        # pc.addTrack(AudioStreamTrack(track))
 
-    # handle offer
     await pc.setRemoteDescription(offer)
 
-    # send answer
     answer = await pc.createAnswer()
     await pc.setLocalDescription(answer)
-    print("Response sent")
     return web.Response(
         content_type="application/json",
         text=json.dumps(
@@ -166,7 +148,6 @@ async def offer(request):
 
 
 async def on_shutdown(app):
-    # close peer connections
     coros = [pc.close() for pc in pcs]
     await asyncio.gather(*coros)
     pcs.clear()

server_multithreaded.py

@@ -3,21 +3,21 @@ import configparser
 import datetime
 import io
 import json
-from utils.log_utils import logger
 import os
 import threading
 import uuid
 import wave
 from concurrent.futures import ThreadPoolExecutor
+from aiohttp import web
 
 import jax.numpy as jnp
-
 from aiortc import MediaStreamTrack, RTCPeerConnection, RTCSessionDescription
 from aiortc.contrib.media import (MediaRelay)
 from av import AudioFifo
 from sortedcontainers import SortedDict
 from whisper_jax import FlaxWhisperPipline
 
+from utils.log_utils import logger
 from utils.server_utils import Mutex
 
 ROOT = os.path.dirname(__file__)

stream_client.py

@@ -1,7 +1,6 @@
 import ast
 import asyncio
 import configparser
-from utils.log_utils import logger
 import time
 import uuid
 
@@ -12,6 +11,7 @@ import stamina
 from aiortc import (RTCPeerConnection, RTCSessionDescription)
 from aiortc.contrib.media import (MediaPlayer, MediaRelay)
 
+from utils.log_utils import logger
 from utils.server_utils import Mutex
 
 file_lock = Mutex(open("test_sm_6.txt", "a"))

utils/file_utils.py

@@ -2,6 +2,7 @@ import configparser
 
 import boto3
 import botocore
+
 from log_utils import logger
 
 config = configparser.ConfigParser()

utils/text_utilities.py

@@ -2,13 +2,14 @@ import configparser
 
 import nltk
 import torch
-from log_utils import logger
 from nltk.corpus import stopwords
 from nltk.tokenize import word_tokenize
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 from transformers import BartTokenizer, BartForConditionalGeneration
 
+from log_utils import logger
+
 nltk.download('punkt', quiet=True)
 
 config = configparser.ConfigParser()

whisjax.py

@@ -18,10 +18,10 @@ import moviepy.editor
 import moviepy.editor
 import nltk
 import yt_dlp as youtube_dl
-from utils.log_utils import logger
 from whisper_jax import FlaxWhisperPipline
 
 from utils.file_utils import upload_files, download_files
+from utils.log_utils import logger
 from utils.text_utilities import summarize, post_process_transcription
 from utils.viz_utilities import create_wordcloud, create_talk_diff_scatter_viz
 

whisjax_realtime.py

@@ -7,12 +7,12 @@ from datetime import datetime
 
 import jax.numpy as jnp
 import pyaudio
-from utils.log_utils import logger
 from pynput import keyboard
 from termcolor import colored
 from whisper_jax import FlaxWhisperPipline
 
 from utils.file_utils import upload_files
+from utils.log_utils import logger
 from utils.text_utilities import summarize, post_process_transcription
 from utils.viz_utilities import create_wordcloud, create_talk_diff_scatter_viz