idk

app.py

@@ -29,19 +29,28 @@ import soundfile as sf
 
 from model import get_pretrained_model, language_to_models
 
-title = "# Texto a Voz ()"
+title = "# Next-gen Kaldi: Text-to-speech (TTS)"
 
 description = """
-Este espacio muestra el comó convertir texto a voz con tecnologías como Piper, Kaldi, y Next-gen.
+This space shows how to convert text to speech with Next-gen Kaldi.
 
-El proceso de convertir sucede en un CPU con un contenedor docker dado por la plataforma Hugging Face.
+It is running on CPU within a docker container provided by Hugging Face.
 
-Si quiere obtener mas información visite los sigientes links:
+See more information by visiting the following links:
 
 - <https://github.com/k2-fsa/sherpa-onnx>
 
-Tambien existen aplicaciones android con esta tecnología en el siguiente enlace:
-<https://huggingface.co/csukuangfj/sherpa-onnx-apk/tree/main/tts>
+If you want to deploy it locally, please see
+<https://k2-fsa.github.io/sherpa/>
+
+If you want to use Android APKs, please see
+<https://k2-fsa.github.io/sherpa/onnx/tts/apk.html>
+
+If you want to use Android text-to-speech engine APKs, please see
+<https://k2-fsa.github.io/sherpa/onnx/tts/apk-engine.html>
+
+If you want to download an all-in-one exe for Windows, please see
+<https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models>
 
 """
 
@@ -148,12 +157,21 @@ with demo:
     )
 
     with gr.Tabs():
-        with gr.TabItem("Por favor ingresa tu texto"):
+        with gr.TabItem("Please input your text"):
             input_text = gr.Textbox(
-                label="Texto",
-                info="Tu texto",
+                label="Input text",
+                info="Your text",
                 lines=3,
-                placeholder="Por favor ingresa tu texto aquí",
+                placeholder="Please input your text here",
+            )
+
+            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",
             )
 
             input_speed = gr.Slider(
@@ -161,21 +179,38 @@ with demo:
                 maximum=10,
                 value=1,
                 step=0.1,
-                label="Velocidad",
+                label="Speed (larger->faster; smaller->slower)",
             )
 
-            input_button = gr.Button("Convertir")
+            input_button = gr.Button("Submit")
 
-            output_audio = gr.Audio(label="Salida")
+            output_audio = gr.Audio(label="Output")
 
             output_info = gr.HTML(label="Info")
 
+            gr.Examples(
+                examples=examples,
+                fn=process,
+                inputs=[
+                    language_radio,
+                    model_dropdown,
+                    input_text,
+                    input_sid,
+                    input_speed,
+                ],
+                outputs=[
+                    output_audio,
+                    output_info,
+                ],
+            )
+
         input_button.click(
             process,
             inputs=[
                 language_radio,
                 model_dropdown,
                 input_text,
+                input_sid,
                 input_speed,
             ],
             outputs=[