Merge pull request #22 from Monadical-SAS/whisper-jax-gokul

Merge with main branch

.gitignore

@@ -165,8 +165,13 @@ transcript.txt
 transcript_timestamps.txt
 *.html
 *.pkl
+transcript_*.txt
+test_*.txt
+*.png
 *.ini
 test_samples/
 *.wav
-
-.vscode/
+*.mp3
+*.m4a
+.DS_Store/
+.vscode/

utils/viz_utilities.py

@@ -3,6 +3,8 @@ from wordcloud import WordCloud, STOPWORDS
 from nltk.corpus import stopwords
 import collections
 import spacy
+import os
+from pathlib import Path
 import pickle
 import ast
 import pandas as pd
@@ -66,7 +68,8 @@ def create_talk_diff_scatter_viz(timestamp, real_time=False):
     agenda_topics = []
     agenda = []
     # Load the agenda
-    with open("../agenda-headers.txt", "r") as f:
+    path = Path(__file__)
+    with open(os.path.join(os.getcwd(), "agenda-headers.txt"), "r") as f:
         for line in f.readlines():
             if line.strip():
                 agenda.append(line.strip())

whisjax.py

@@ -22,9 +22,9 @@ from urllib.parse import urlparse
 from whisper_jax import FlaxWhisperPipline
 
 from datetime import datetime
-from reflector.utils.file_utilities import upload_files, download_files
-from reflector.utils.viz_utilities import create_wordcloud, create_talk_diff_scatter_viz
-from reflector.utils.text_utilities import summarize, post_process_transcription
+from utils.file_utilities import upload_files, download_files
+from utils.viz_utilities import create_wordcloud, create_talk_diff_scatter_viz
+from utils.text_utilities import summarize, post_process_transcription
 
 nltk.download('punkt', quiet=True)
 nltk.download('stopwords', quiet=True)

whisjax_realtime.py

@@ -7,9 +7,9 @@ from pynput import keyboard
 import jax.numpy as jnp
 import wave
 from datetime import datetime
-from reflector.utils.file_utilities import upload_files
-from reflector.utils.viz_utilities import create_wordcloud, create_talk_diff_scatter_viz
-from reflector.utils.text_utilities import summarize, post_process_transcription
+from utils.file_utilities import upload_files
+from utils.viz_utilities import create_wordcloud, create_talk_diff_scatter_viz
+from utils.text_utilities import summarize, post_process_transcription
 from loguru import logger
 import time
 from termcolor import colored