try again

app.py

@@ -3,20 +3,21 @@ import parselmouth
 from parselmouth.praat import call
 import numpy as np
 
-# def greet(name):
-#     return "Hello " + name + "!!"
-
-# demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-# demo.launch()
-
-
 def get_pitch(audio_data):
-    rate, data = audio_data  # Assuming Gradio passes (sampling_rate, numpy_array)
-    sound = parselmouth.Sound(values=np.array(data, dtype='float64'), sampling_frequency=rate)
-    pitch = call(sound, "To Pitch", 0.0, 75, 500)
-    pitch_values = pitch.selected_array['frequency']
-    return "Pitch frequencies: " + str(pitch_values)
+    rate, data = audio_data
+    if data.ndim > 1:  # Check if the audio is stereo or multi-channel
+        data = np.mean(data, axis=1)  # Convert to mono by averaging channels
+    
+    # Convert data to float64 for compatibility with Parselmouth
+    data = data.astype('float64')
+
+    sound = parselmouth.Sound(values=data, sampling_frequency=rate)
+    try:
+        pitch = call(sound, "To Pitch", 0.0, 75, 500)
+        pitch_values = pitch.selected_array['frequency']
+        return "Pitch frequencies: " + str(pitch_values)
+    except Exception as e:
+        return "Error in pitch extraction: " + str(e)
 
 demo = gr.Interface(fn=get_pitch, inputs="audio", outputs="text")
 demo.launch()
-