Update app.py

app.py

@@ -2,15 +2,11 @@ import gradio as gr
 import os 
 import shutil
 
-
 from huggingface_hub import snapshot_download
 import numpy as np
 from scipy.io import wavfile
 
 
-
-
-
 model_ids = [
     'suno/bark',
 ]
@@ -18,8 +14,6 @@ for model_id in model_ids:
     model_name = model_id.split('/')[-1]
     snapshot_download(model_id, local_dir=f'checkpoints/{model_name}')
 
-
-
 from TTS.tts.configs.bark_config import BarkConfig
 from TTS.tts.models.bark import Bark
 
@@ -48,7 +42,7 @@ def infer(prompt, input_wav_file):
     shutil.move(source_path, os.path.join(destination_path, f"{file_name}.wav"))
 
 
-    text = "Hello, my name is Manmay , how are you?"
+    text = prompt
 
     # with random speaker
     #output_dict = model.synthesize(text, config, speaker_id="random", voice_dirs=None)
@@ -65,4 +59,11 @@ def infer(prompt, input_wav_file):
    
     return "output.wav"
 
-gr.Interface(fn=infer, inputs=[gr.Textbox(), gr.Audio(type="filepath", source="upload")], outputs=[gr.Audio()]).launch()
+gr.Interface(fn=infer, 
+             inputs=[gr.Textbox(label="Text to speech prompt"), 
+                     gr.Audio(
+                         label="WAV voice to clone", 
+                         type="filepath",
+                         source="upload")],
+             outputs=[gr.Audio()], 
+             title="Instant Voice Cloning").launch()