Update app.py

app.py

@@ -46,7 +46,7 @@ def synthesize_tts(
         if speaker_wavs:
             # Process each uploaded file
             for speaker_wav in speaker_wavs:
-                speaker_wav_bytes = speaker_wav.value
+                speaker_wav_bytes = speaker_wav.read()
                 # Convert the uploaded audio file to a WAV format using pydub
                 try:
                     audio = AudioSegment.from_file(io.BytesIO(speaker_wav_bytes))
@@ -105,10 +105,10 @@ inputs = [
     gr.Textbox(value="Hello, World!", label="Text to Synthesize"),
     gr.File(file_types=["audio"], label="Speaker WAV files (optional)", file_count="multiple"),
     gr.Textbox(value="Ana Florence", label="Speaker Index"),
-    gr.Textbox(value="ja", label="Language"),
+    gr.Textbox(value="en", label="Language"),
     gr.Slider(0, 1, value=0.65, step=0.01, label="Temperature"),
-    gr.Slider(2.0, 2, value=1.0, step=0.1, label="Length Penalty"),
-    gr.Slider(1, 10, value=2.0, step=0.1, label="Repetition Penalty"),
+    gr.Slider(0.5, 2, value=1.0, step=0.1, label="Length Penalty"),
+    gr.Slider(1.0, 10.0, value=2.0, step=0.1, label="Repetition Penalty"),
     gr.Slider(1, 100, value=50, step=1, label="Top-K"),
     gr.Slider(0, 1, value=0.8, step=0.01, label="Top-P"),
     gr.Slider(0.5, 2, value=1.0, step=0.01, label="Speed"),