test

app.py

@@ -56,6 +56,18 @@ css = """
 """
 
 
+def update_model_dropdown(language: str):
+    if language in language_to_models:
+        choices = language_to_models[language]
+        return gr.Dropdown(
+            choices=choices,
+            value=choices[0],
+            interactive=True,
+        )
+
+    raise ValueError(f"Unsupported language: {language}")
+
+
 def build_html_output(s: str, style: str = "result_item_success"):
     return f"""
     <div class='result'>
@@ -66,12 +78,13 @@ def build_html_output(s: str, style: str = "result_item_success"):
     """
 
 
-def process(language: str, repo_id: str, text: str, speed: float):
-    logging.info(f"Input text: {text}. Speed: {speed}")
+def process(language: str, repo_id: str, text: str, sid: str, speed: float):
+    logging.info(f"Input text: {text}. sid: {sid}, speed: {speed}")
+    sid = int(sid)
     tts = get_pretrained_model(repo_id, speed)
 
     start = time.time()
-    audio = tts.generate(text)
+    audio = tts.generate(text, sid=sid)
     end = time.time()
 
     if len(audio.samples) == 0:
@@ -91,7 +104,7 @@ def process(language: str, repo_id: str, text: str, speed: float):
     """
 
     logging.info(info)
-    logging.info(f"\nrepo_id: {repo_id}\ntext: {text}\nspeed: {speed}")
+    logging.info(f"\nrepo_id: {repo_id}\ntext: {text}\nsid: {sid}\nspeed: {speed}")
 
     filename = str(uuid.uuid4())
     filename = f"{filename}.wav"
@@ -110,6 +123,25 @@ demo = gr.Blocks(css=css)
 
 with demo:
     gr.Markdown(title)
+    language_choices = list(language_to_models.keys())
+
+    language_radio = gr.Radio(
+        label="Idioma",
+        choices=language_choices,
+        value=language_choices[0],
+    )
+
+    model_dropdown = gr.Dropdown(
+        choices=language_to_models[language_choices[0]],
+        label="Seleccion un modelo",
+        value=language_to_models[language_choices[0]][0],
+    )
+
+    language_radio.change(
+        update_model_dropdown,
+        inputs=language_radio,
+        outputs=model_dropdown,
+    )
 
     with gr.Tabs():
         with gr.TabItem("Por favor ingresa tu texto"):
@@ -120,6 +152,16 @@ with demo:
                 placeholder="Por favor ingresa tu texto aquí",
             )
 
+            input_sid = gr.Textbox(
+                label="Speaker ID",
+                info="Speaker ID",
+                lines=1,
+                max_lines=1,
+                value="0",
+                placeholder="Speaker ID. Valid only for mult-speaker model",
+            )
+            print(input_sid)
+
             input_speed = gr.Slider(
                 minimum=0.1,
                 maximum=10,
@@ -137,7 +179,10 @@ with demo:
         input_button.click(
             process,
             inputs=[
+                language_radio,
+                model_dropdown,
                 input_text,
+                input_sid,
                 input_speed,
             ],
             outputs=[