Update app.py

app.py

@@ -266,37 +266,38 @@ def process_document(file):
 # Function to handle speech-to-text conversion
 
 #def transcribe_audio(audio):
-#    sr, y = audio
-#    if y.ndim > 1:
-#        y = y.mean(axis=1)
-#    y = y.astype(np.float32)
-#    y /= np.max(np.abs(y))
-#    return transcriber({"sampling_rate": sr, "raw": y})["text"]
-
-#Quick Fixes You Can Try First:
-
-def transcribe_audio(audio):
     sr, y = audio
     if y.ndim > 1:
         y = y.mean(axis=1)
     y = y.astype(np.float32)
+    y /= np.max(np.abs(y))
+    return transcriber({"sampling_rate": sr, "raw": y})["text"]
+
+"""
+#Quick Fixes You Can Try First:
+
+#def transcribe_audio(audio):
+#    sr, y = audio
+#    if y.ndim > 1:
+#        y = y.mean(axis=1)
+#    y = y.astype(np.float32)
     
     # Improved normalization
-    max_val = np.max(np.abs(y))
-    if max_val > 0:
-        y /= max_val
+#    max_val = np.max(np.abs(y))
+#    if max_val > 0:
+#        y /= max_val
     
     # Use better model
-    better_transcriber = pipeline(
-        "automatic-speech-recognition",
-        model="openai/whisper-small.en",  # More accurate
-        chunk_length_s=30
-    )
+#    better_transcriber = pipeline(
+#        "automatic-speech-recognition",
+#        model="openai/whisper-small.en",  # More accurate
+#        chunk_length_s=30
+#    )
     
-    return better_transcriber({"sampling_rate": sr, "raw": y})["text"]
+#    return better_transcriber({"sampling_rate": sr, "raw": y})["text"]
 
 # the remaining is the same 
-
+"""