edit

app.py

@@ -1,6 +1,5 @@
 from typing import Tuple, Optional, Any
-
-import numpy as numpy
+import numpy as np
 import gradio as gradio_module
 from PIL import Image
 from transformers import (
@@ -88,8 +87,8 @@ def run_tts(summary_text: str) -> Optional[Tuple[int, Any]]:
     sampling_rate_int: int = int(tts_output["sampling_rate"])
     audio_array = tts_output["audio"]
 
-    if not isinstance(audio_array, numpy.ndarray):
-        audio_array = numpy.array(audio_array)
+    audio_array = np.array(audio_array, dtype=np.float32)
+    audio_array = np.clip(audio_array, -1.0, 1.0)
 
     return sampling_rate_int, audio_array