organize imports

utils/config.ini

@@ -1,24 +1,24 @@
 [DEFAULT]
 #SetexceptionruleforOpenMPerrortoallowduplicatelibinitialization
-KMP_DUPLICATE_LIB_OK=TRUE
+KMP_DUPLICATE_LIB_OK = TRUE
 #ExportOpenAIAPIKey
-OPENAI_APIKEY=
+OPENAI_APIKEY =
 #ExportWhisperModelSize
-WHISPER_MODEL_SIZE=tiny
-WHISPER_REAL_TIME_MODEL_SIZE=tiny
+WHISPER_MODEL_SIZE = tiny
+WHISPER_REAL_TIME_MODEL_SIZE = tiny
 #AWSconfig
-AWS_ACCESS_KEY=***REMOVED***
-AWS_SECRET_KEY=***REMOVED***
-BUCKET_NAME=reflector-bucket
+AWS_ACCESS_KEY = ***REMOVED***
+AWS_SECRET_KEY = ***REMOVED***
+BUCKET_NAME = reflector-bucket
 #Summarizerconfig
-SUMMARY_MODEL=facebook/bart-large-cnn
-INPUT_ENCODING_MAX_LENGTH=1024
-MAX_LENGTH=2048
-BEAM_SIZE=6
-MAX_CHUNK_LENGTH=1024
-SUMMARIZE_USING_CHUNKS=YES
+SUMMARY_MODEL = facebook/bart-large-cnn
+INPUT_ENCODING_MAX_LENGTH = 1024
+MAX_LENGTH = 2048
+BEAM_SIZE = 6
+MAX_CHUNK_LENGTH = 1024
+SUMMARIZE_USING_CHUNKS = YES
 #Audiodevice
-BLACKHOLE_INPUT_AGGREGATOR_DEVICE_NAME=aggregator
-AV_FOUNDATION_DEVICE_ID=1
+BLACKHOLE_INPUT_AGGREGATOR_DEVICE_NAME = aggregator
+AV_FOUNDATION_DEVICE_ID = 1
 # LLM PATH
-LLM_PATH=
+LLM_PATH =

utils/format_output.py

@@ -0,0 +1,32 @@
+import json
+
+with open("../artefacts/meeting_titles_and_summaries.txt", "r") as f:
+    outputs = f.read()
+
+outputs = json.loads(outputs)
+
+transcript_file = open("../artefacts/meeting_transcript.txt", "a")
+title_desc_file = open("../artefacts/meeting_title_description.txt", "a")
+summary_file = open("../artefacts/meeting_summary.txt", "a")
+
+for item in outputs["topics"]:
+    transcript_file.write(item["transcript"])
+    summary_file.write(item["description"])
+
+    title_desc_file.write("TITLE: \n")
+    title_desc_file.write(item["title"])
+    title_desc_file.write("\n")
+
+    title_desc_file.write("DESCRIPTION: \n")
+    title_desc_file.write(item["description"])
+    title_desc_file.write("\n")
+
+    title_desc_file.write("TRANSCRIPT: \n")
+    title_desc_file.write(item["transcript"])
+    title_desc_file.write("\n")
+
+    title_desc_file.write("---------------------------------------- \n\n")
+
+transcript_file.close()
+title_desc_file.close()
+summary_file.close()

utils/text_utilities.py

@@ -6,8 +6,8 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 from transformers import BartForConditionalGeneration, BartTokenizer
 
-from utils.log_utils import logger
-from utils.run_utils import config
+from log_utils import logger
+from run_utils import config
 
 nltk.download('punkt', quiet=True)
 
@@ -171,7 +171,7 @@ def summarize(transcript_text, timestamp,
         output_filename = "real_time_" + output_filename
 
     if summarize_using_chunks != "YES":
-        inputs = tokenizer.\
+        inputs = tokenizer. \
             batch_encode_plus([transcript_text], truncation=True,
                               padding='longest',
                               max_length=int(config["DEFAULT"]["INPUT_ENCODING_MAX_LENGTH"]),

utils/viz_utilities.py

@@ -13,7 +13,7 @@ from wordcloud import STOPWORDS, WordCloud
 en = spacy.load('en_core_web_md')
 spacy_stopwords = en.Defaults.stop_words
 
-STOPWORDS = set(STOPWORDS).union(set(stopwords.words("english"))).\
+STOPWORDS = set(STOPWORDS).union(set(stopwords.words("english"))). \
     union(set(spacy_stopwords))
 
 
@@ -24,7 +24,7 @@ def create_wordcloud(timestamp, real_time=False):
     """
     filename = "transcript"
     if real_time:
-        filename = "real_time_" + filename + "_" +\
+        filename = "real_time_" + filename + "_" + \
                    timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".txt"
     else:
         filename += "_" + timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".txt"
@@ -47,7 +47,7 @@ def create_wordcloud(timestamp, real_time=False):
 
     wordcloud_name = "wordcloud"
     if real_time:
-        wordcloud_name = "real_time_" + wordcloud_name + "_" +\
+        wordcloud_name = "real_time_" + wordcloud_name + "_" + \
                          timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".png"
     else:
         wordcloud_name += "_" + timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".png"
@@ -57,12 +57,12 @@ def create_wordcloud(timestamp, real_time=False):
 
 def create_talk_diff_scatter_viz(timestamp, real_time=False):
     """
-    Perform agenda vs transription diff to see covered topics.
+    Perform agenda vs transcription diff to see covered topics.
     Create a scatter plot of words in topics.
     :return: None. Saved locally.
     """
-    spaCy_model = "en_core_web_md"
-    nlp = spacy.load(spaCy_model)
+    spacy_model = "en_core_web_md"
+    nlp = spacy.load(spacy_model)
     nlp.add_pipe('sentencizer')
 
     agenda_topics = []
@@ -75,12 +75,11 @@ def create_talk_diff_scatter_viz(timestamp, real_time=False):
                 agenda_topics.append(line.split(":")[0])
 
     # Load the transcription with timestamp
-    filename = ""
     if real_time:
-        filename = "./artefacts/real_time_transcript_with_timestamp_" +\
+        filename = "./artefacts/real_time_transcript_with_timestamp_" + \
                    timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".txt"
     else:
-        filename = "./artefacts/transcript_with_timestamp_" +\
+        filename = "./artefacts/transcript_with_timestamp_" + \
                    timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".txt"
     with open(filename) as f:
         transcription_timestamp_text = f.read()
@@ -142,7 +141,7 @@ def create_talk_diff_scatter_viz(timestamp, real_time=False):
 
     df = df.apply(create_new_columns, axis=1)
 
-    # Count the number of items covered and calculatre the percentage
+    # Count the number of items covered and calculate the percentage
     num_covered_items = sum(covered_items.values())
     percentage_covered = num_covered_items / len(agenda) * 100
 
@@ -158,7 +157,7 @@ def create_talk_diff_scatter_viz(timestamp, real_time=False):
     # Save df, mappings for further experimentation
     df_name = "df"
     if real_time:
-        df_name = "real_time_" + df_name + "_" +\
+        df_name = "real_time_" + df_name + "_" + \
                   timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".pkl"
     else:
         df_name += "_" + timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".pkl"
@@ -169,7 +168,7 @@ def create_talk_diff_scatter_viz(timestamp, real_time=False):
 
     mappings_name = "mappings"
     if real_time:
-        mappings_name = "real_time_" + mappings_name + "_" +\
+        mappings_name = "real_time_" + mappings_name + "_" + \
                         timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".pkl"
     else:
         mappings_name += "_" + timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".pkl"