Update app.py

app.py

@@ -458,37 +458,37 @@ pipe_asr = pipeline("automatic-speech-recognition", model=model, tokenizer=proce
 
 base_audio_drive = "/data/audio"
 
-# def transcribe_function(stream, new_chunk):
-#     try:
-#         sr, y = new_chunk[0], new_chunk[1]
-#     except TypeError:
-#         print(f"Error chunk structure: {type(new_chunk)}, content: {new_chunk}")
-#         return stream, "", None
-
-#     y = y.astype(np.float32) / np.max(np.abs(y))
-
-#     if stream is not None:
-#         stream = np.concatenate([stream, y])
-#     else:
-#         stream = y
-
-#     result = pipe_asr({"array": stream, "sampling_rate": sr}, return_timestamps=False)
-
-#     full_text = result.get("text","")
-    
-#     return stream, full_text, result
-
-
 def transcribe_function(stream, new_chunk):
-    sr, y = new_chunk[0], new_chunk[1]
+    try:
+        sr, y = new_chunk[0], new_chunk[1]
+    except TypeError:
+        print(f"Error chunk structure: {type(new_chunk)}, content: {new_chunk}")
+        return stream, "", None
+
     y = y.astype(np.float32) / np.max(np.abs(y))
+
     if stream is not None:
         stream = np.concatenate([stream, y])
     else:
         stream = y
+
     result = pipe_asr({"array": stream, "sampling_rate": sr}, return_timestamps=False)
-    full_text = result.get("text", "")
-    return stream, full_text  # Return the transcribed text
+
+    full_text = result.get("text","")
+    
+    return stream, full_text, result
+
+
+# def transcribe_function(stream, new_chunk):
+#     sr, y = new_chunk[0], new_chunk[1]
+#     y = y.astype(np.float32) / np.max(np.abs(y))
+#     if stream is not None:
+#         stream = np.concatenate([stream, y])
+#     else:
+#         stream = y
+#     result = pipe_asr({"array": stream, "sampling_rate": sr}, return_timestamps=False)
+#     full_text = result.get("text", "")
+#     return stream, full_text  # Return the transcribed text