Upload 2 files

app.py

@@ -0,0 +1,87 @@
+import streamlit as st
+import whisper
+from transformers import pipeline
+import spacy
+from summa import keywords
+import datetime
+import os
+
+@st.cache_resource
+def load_models():
+    whisper_model = whisper.load_model("base")
+    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+    nlp = spacy.load("en_core_web_sm")
+    return whisper_model, summarizer, nlp
+
+def extract_action_items(text, nlp):
+    doc = nlp(text)
+    actions = []
+    
+    for sent in doc.sents:
+        for token in sent:
+            if token.dep_ == "ROOT" and token.pos_ == "VERB":
+                action = {
+                    "text": sent.text,
+                    "responsible": [],
+                    "deadline": []
+                }
+                
+                for ent in sent.ents:
+                    if ent.label_ == "PERSON":
+                        action["responsible"].append(ent.text)
+                    elif ent.label_ == "DATE":
+                        action["deadline"].append(ent.text)
+                
+                actions.append(action)
+                break
+    return actions
+
+def main():
+    st.title("🤖 Smart AI Meeting Assistant")
+    
+    whisper_model, summarizer, nlp = load_models()
+    
+    audio_file = st.file_uploader("Upload meeting audio", type=["wav", "mp3", "m4a"])
+    
+    if audio_file is not None:
+        file_path = f"uploaded_audio_{datetime.datetime.now().timestamp()}"
+        with open(file_path, "wb") as f:
+            f.write(audio_file.getbuffer())
+            
+        st.subheader("Meeting Transcription")
+        with st.spinner("Transcribing audio..."):
+            result = whisper_model.transcribe(file_path)
+            transcript = result["text"]
+        st.write(transcript)
+        os.remove(file_path)
+        
+        st.subheader("Meeting Summary")
+        with st.spinner("Generating summary..."):
+            truncated_text = transcript[:1024]
+            summary = summarizer(truncated_text, max_length=150, min_length=50)[0]['summary_text']
+        st.write(summary)
+        
+        st.subheader("🚀 Action Items")
+        actions = extract_action_items(transcript, nlp)
+        
+        if not actions:
+            st.write("No action items detected")
+        else:
+            for i, action in enumerate(actions, 1):
+                responsible = ", ".join(action["responsible"]) or "Unassigned"
+                deadline = ", ".join(action["deadline"]) or "No deadline"
+                st.markdown(f"""
+                **Action {i}**
+                - Task: {action["text"]}
+                - Responsible: {responsible}
+                - Deadline: {deadline}
+                """)
+        
+        st.subheader("🔑 Key Terms")
+        # Fixed keyword processing
+        key_phrases_result = keywords.keywords(transcript) or ""
+        key_phrases = [kp.strip() for kp in key_phrases_result.split("\n") if kp.strip()]
+        st.write(", ".join(key_phrases) if key_phrases else "No key terms extracted")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,10 @@
+# requirements.txt (updated)
+streamlit==1.27.0
+openai-whisper==20231117
+torch==2.1.0
+transformers==4.35.2
+spacy==3.7.2
+summa==1.2.0  # Changed from 1.2.3 to available version
+python-magic==0.4.27
+ffmpeg-python==0.2.0
+en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.0/en_core_web_sm-3.7.0-py3-none-any.whl