Core code

app.py

@@ -0,0 +1,52 @@
+import streamlit as st
+import speech_recognition as sr
+from transformers import pipeline
+import re
+
+# Load NLP models
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+
+def extract_info(text):
+    candidate_labels = ["project status", "risks", "questions", "administration"]
+    result = classifier(text, candidate_labels)
+    return result
+
+def normalize_text(text):
+    text = text.lower()
+    text = re.sub(r'\s+', ' ', text)
+    return text
+
+st.title("Audio to Text Processing and Categorization")
+
+audio_file = st.file_uploader("Upload an audio file", type=["wav"])
+
+if audio_file is not None:
+    st.audio(audio_file, format='audio/wav')
+
+    # Convert audio to text
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(audio_file) as source:
+        audio_data = recognizer.record(source)
+        text = recognizer.recognize_google(audio_data)
+
+    st.write("Transcribed Text:")
+    st.write(text)
+
+    # NLP processing
+    summary = summarizer(text, max_length=150, min_length=30, do_sample=False)
+
+    st.write("Summarized Text:")
+    st.write(summary[0]['summary_text'])
+
+    # Information extraction
+    extracted_info = extract_info(summary[0]['summary_text'])
+
+    st.write("Extracted Information:")
+    st.write(extracted_info)
+
+    # Text normalization
+    normalized_text = normalize_text(str(extracted_info))
+
+    st.write("Normalized Text:")
+    st.write(normalized_text)