Update app.py

app.py

@@ -1,30 +1,31 @@
 import gradio as gr
 from TTS.api import TTS
 
-tts = TTS("tts_models/multilingual/multi-dataset/xtts_v1")
-tts.to("cuda")
+model_id = "tts_models/multilingual/multi-dataset/xtts_v1"
+device = "cuda"
 
+tts = TTS
+tts.to(device)
 
-def predict(prompt, language, audio_file_pth, agree):
-    if agree == True:
-        tts.tts_to_file(
-            text=prompt,
-            file_path="output.wav",
-            speaker_wav=audio_file_pth,
-            language=language,
-        )
 
-        return (
-            gr.make_waveform(
-                audio="output.wav",
-            ),
-            "output.wav",
-        )
-    else:
-        gr.Warning("Please accept the Terms & Condition!")
+def predict(prompt, audio_file_pth):
+    
+    tts.tts_to_file(
+        text=prompt,
+        file_path="output.wav",
+        speaker_wav=audio_file_pth,
+        language=language,
+    )
+
+    return (
+        gr.make_waveform(
+            audio="output.wav",
+        ),
+        "output.wav",
+    )
 
 
-title = "Coqui🐸 XTTS"
+title = "Coquib🐸 XTTS - Spanish Demo"
 
 description = """
 <a href="https://huggingface.co/coqui/XTTS-v1">XTTS</a> is a Voice generation model that lets you clone voices into different languages by using just a quick 3-second audio clip. 
@@ -47,67 +48,20 @@ article = """
 </div>
 """
 
-examples = [
-    [
-        "Once when I was six years old I saw a magnificent picture.",
-        "en",
-        "examples/female.wav",
-        True,
-    ],
-    [
-        "Lorsque j'avais six ans j'ai vu, une fois, une magnifique image.",
-        "fr",
-        "examples/male.wav",
-        True,
-    ],
-    [
-        "Un tempo lontano, quando avevo sei anni, vidi un magnifico disegno.",
-        "it",
-        "examples/female.wav",
-        True,
-    ],
-]
-
 gr.Interface(
     fn=predict,
     inputs=[
         gr.Textbox(
-            label="Text Prompt",
-            info="One or two sentences at a time is better",
-            value="It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
-        ),
-        gr.Dropdown(
-            label="Language",
-            info="Select an output language for the synthesised speech",
-            choices=[
-                "en",
-                "es",
-                "fr",
-                "de",
-                "it",
-                "pt",
-                "pl",
-                "tr",
-                "ru",
-                "nl",
-                "cz",
-                "ar",
-                "zh-cn",
-            ],
-            max_choices=1,
-            value="en",
+            label="Texto",
+            info="Una o dos frases es suficiente-",
+            value="Clibrain es una empresa que desarrolla soluciones basadas en inteligencia artificial en español.",
         ),
         gr.Audio(
-            label="Reference Audio",
-            info="Click on the ✎ button to upload your own target speaker audio",
+            label="Audio de referencia",
+            info="Haz clic en el botón ✎ para subir tu propio audio o del hablante objetivo",
             type="filepath",
             value="examples/female.wav",
         ),
-        gr.Checkbox(
-            label="Agree",
-            value=False,
-            info="I agree to the terms of the Coqui Public Model License at https://coqui.ai/cpml",
-        ),
     ],
     outputs=[
         gr.Video(label="Waveform Visual"),