Create app.py

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+
+model = gr.Interface.load("huggingface/pyannote/voice-activity-detection")
+
+#load input file and resample to 16kHz
+def load_data(path):
+    speech, sampling_rate = librosa.load(path)
+    if len(speech.shape) > 1:
+        speech = speech[:,0] + speech[:,1]
+    if sampling_rate != 16000:
+        speech = librosa.resample(speech, sampling_rate,16000)
+    return speech
+    
+def inference(path):
+    audio = load_data(path)
+
+inputs = gr.inputs.Audio(label="Input Audio", type="filepath", source="microphone")
+outputs = gr.outputs.Label(type="auto", label = "Voice timestamps")
+title = "Voice Activity Detection"
+description = "Record or upload an audio file and detected human voices will be timestamped."
+article = "<a href = 'pyannote, https://github.com/pyannote/pyannote-audio"
+
+gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, theme="dark").launch(debug=True)
+
+
+
+