Update app.py

app.py

@@ -3,14 +3,34 @@ asr = pipeline(task="automatic-speech-recognition",
                model="distil-whisper/distil-small.en")
 import os
 import gradio as gr
+from pydub import AudioSegment
 
 demo = gr.Blocks()
 def transcribe_speech(filepath):
     if filepath is None:
         gr.Warning("No audio found, please retry.")
         return ""
-    output = asr(filepath)
-    return output["text"]
+
+    # Load audio using pydub
+    audio = AudioSegment.from_file(filepath)
+    chunk_length_ms = 30 * 1000  # 30 seconds
+    chunks = [audio[i:i + chunk_length_ms] for i in range(0, len(audio), chunk_length_ms)]
+
+    full_transcription = ""
+
+    for i, chunk in enumerate(chunks):
+        # Export chunk to temporary wav file
+        chunk_path = f"chunk_{i}.wav"
+        chunk.export(chunk_path, format="wav")
+
+        # Transcribe the chunk
+        result = asr(chunk_path)
+        full_transcription += result["text"] + " "
+
+        # Clean up (optional)
+        os.remove(chunk_path)
+
+    return full_transcription.strip()
     
 mic_transcribe = gr.Interface(
     fn=transcribe_speech,