Update app.py

app.py

@@ -17,8 +17,8 @@ VOICE_OPTIONS = [
 def inference(
     text,
     voice,
-    emotion_option,
-    preset_option,
+    Emotion,
+    Preset,
 ):
     
     texts = [text]
@@ -28,13 +28,13 @@ def inference(
     Happy_tone = "[I am so happy]"
     Scared_tone = "[I am so scared]"
 
-    if emotion_option == "Angry":
+    if Emotion == "Angry":
         text = Angry_tone + text
-    if emotion_option == "Sad":
+    if Emotion == "Sad":
         text = Sad_tone + text
-    if emotion_option == "Happy":
+    if Emotion == "Happy":
         text = Happy_tone + text
-    if emotion_option == "Scared":
+    if Emotion == "Scared":
         text = Scared_tone + text
 
     voices = [voice]
@@ -51,7 +51,7 @@ def inference(
             text,
             voice_samples=voice_samples,
             conditioning_latents=conditioning_latents,
-            preset= preset_option,
+            preset= Preset,
             k=1
         ):
             yield (24000, audio_frame.cpu().detach().numpy())
@@ -68,14 +68,13 @@ def main():
         VOICE_OPTIONS, value="jane_eyre", label="Select voice:", type="value"
     )
 
-    emotion_option = gr.Radio(
+    Emotion = gr.Radio(
         ["Angry", "Sad", "Happy", "Scared"],
         type="value",
     )
 
-    preset_option = gr.Radio(
+    Preset = gr.Radio(
         ["ultra_fast", "fast", "standard", "high_quality"],
-        label="ultra_fast for quick inference and high_quality for better inference",
         type="value",
         value="ultra_fast",
     )
@@ -86,8 +85,8 @@ def main():
         inputs=[
             text,
             voice,
-            emotion_option,
-            preset_option,
+            Emotion,
+            Preset,
         ],
         title=title,
         outputs=[output_audio],