commit

app.py

@@ -3,10 +3,11 @@ import os
 import requests
 import json
 from langchain.tools import tool
-import requests
 from typing import TypedDict
 from langgraph.graph import StateGraph
 import gradio as gr
+from pydub import AudioSegment
+import tempfile
 
 MISTRAL_API_KEY = os.getenv("MISTRAL_API_KEY")
 MODEL = "mistral-large-latest"
@@ -17,6 +18,15 @@ class State(TypedDict):
     summary_json: dict
     final_output: str
 
+def convert_to_wav(input_path: str) -> str:
+    if input_path.lower().endswith(".wav"):
+        return input_path  # No conversion needed
+    else:
+        audio = AudioSegment.from_file(input_path)
+        temp_wav_file = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
+        audio.export(temp_wav_file.name, format="wav")
+        return temp_wav_file.name
+
 def transcribe_audio(state: State) -> State:
     model = WhisperModel("base", compute_type="float32")
     segments, _ = model.transcribe(state["file_path"], beam_size=5, language="en")
@@ -24,17 +34,14 @@ def transcribe_audio(state: State) -> State:
     transcript = " ".join(segment.text.strip() for segment in segments)
     return {**state, "transcript": transcript}
 
-
 def summarize_transcript(state: State) -> State:
     prompt = f"""
 You are an AI assistant summarizing meeting transcripts.
-
 Extract the following:
 1. Attendees (Names only, if possible)
 2. Key Discussion Points (bullet format)
 3. Action Items (with owner and deadline, if mentioned)
 4. Decisions Made (if any)
-
 Respond in this format:
 {{
   "attendees": [...],
@@ -42,7 +49,6 @@ Respond in this format:
   "action_items": [...],
   "decisions": [...]
 }}
-
 Transcript:
 \"\"\"{state['transcript']}\"\"\"
 """
@@ -69,12 +75,12 @@ def format_output(state: State) -> State:
     formatted += "📎 Decisions:\n" + "\n".join(f"- {d}" for d in summary["decisions"])
     return {**state, "final_output": formatted}
 
+# Graph setup
 builder = StateGraph(State)
 builder.add_node("transcribe_audio", transcribe_audio)
 builder.add_node("summarize_transcript", summarize_transcript)
 builder.add_node("format_output", format_output)
 
-# Link nodes
 builder.set_entry_point("transcribe_audio")
 builder.add_edge("transcribe_audio", "summarize_transcript")
 builder.add_edge("summarize_transcript", "format_output")
@@ -82,44 +88,34 @@ builder.add_edge("summarize_transcript", "format_output")
 graph = builder.compile()
 
 def process_meeting(file):
-    print(f"Received file: {file}")  # This will print the file path
-    state = {"file_path": file}
-    print(f"State initialized: {state}")  # Check initial state
+    print(f"Received file: {file}")
+    wav_path = convert_to_wav(file)
+    state = {"file_path": wav_path}
+    print(f"State initialized: {state}")
 
     try:
         final_state = graph.invoke(state)
-        print(f"Final State: {final_state}")  # Check final state
+        print(f"Final State: {final_state}")
         return final_state["final_output"]
     except Exception as e:
         print(f"Error: {e}")
         return str(e)
 
-
 with gr.Blocks() as demo:
     gr.Markdown("### 🤖 MeetRecap - AI-Powered Meeting Summarizer")
     gr.Markdown("""
-    Upload your audio file in `.wav` format or record it and get the summary of the meeting i.e Attendees, Key Discussion Points, Action Items, Decisions Made.
+    Upload your audio file (e.g., `.wav`, `.mp3`, `.m4a`) or record it. You'll receive a structured meeting summary including Attendees, Key Points, Action Items, and Decisions.
     """)
 
     with gr.Row():
         with gr.Column():
-            audio_input = gr.Audio(type="filepath", label="🎙️ Upload Meeting (.wav)")
+            audio_input = gr.Audio(type="filepath", label="🎙️ Upload or Record Audio")
             submit_btn = gr.Button("🔍 Summarize")
             clear_btn = gr.Button("🧹 Clear")
         with gr.Column():
             summary_output = gr.Textbox(label="📝 Meeting Summary", lines=20, max_lines=40)
 
-    # 🔁 Optional: Add example audios
-    # gr.Examples(
-    #     examples=[
-    #         "examples/example_meeting_1.wav",
-    #         "examples/example_meeting_2.wav"
-    #     ],
-    #     inputs=audio_input,
-    #     label="🎧 Try Example Audio",
-    #     examples_per_page=0
-    # )
-
     submit_btn.click(fn=process_meeting, inputs=audio_input, outputs=summary_output)
     clear_btn.click(lambda: (None, ""), outputs=[audio_input, summary_output])
+
 demo.launch(share=True)