Update app.py

app.py

@@ -30,6 +30,8 @@ def get_labels(audio_fp, threshold, min_speech_duration_ms, min_silence_duration
                                             return_seconds=True)
     labels_str = []
     labels = []
+
+    uppper_merge_threshold = float(uppper_merge_threshold)
     
     for i, st in enumerate(speech_timestamps):
         labels_str.append(f"{st['start']}\t{st['end']}\tSound {i+1}")
@@ -77,7 +79,7 @@ interface = gr.Interface(
         gr.Number(label="min_speech_duration_ms", value=250, info="default (250)"), 
         gr.Number(label="min_silence_duration_ms", value=100, info="default (100)"),
         gr.Checkbox(label="Auto merge", value=True),
-        gr.Number(label="Gap max threshold value (seconds)", value=1),
+        gr.Textbox(label="Gap max threshold value (seconds)", value=1),
         gr.Number(label="Approx Max Segment Length", value=12)
     ],
     [