Create app.py

app.py

@@ -0,0 +1,21 @@
+import gradio as gr
+from transformers import AutoModelForSpeechSeq2Seq, AutoTokenizer, pipeline
+
+tokenizer = AutoTokenizer.from_pretrained("MarcNg/fastspeech2-vi-infore")
+model = AutoModelForSpeechSeq2Seq.from_pretrained("MarcNg/fastspeech2-vi-infore")
+
+tts_pipeline = pipeline("text-to-speech", model=model, tokenizer=tokenizer)
+
+def text_to_speech(text):
+    output = tts_pipeline(text)
+    return output["audio"].numpy()
+
+iface = gr.Interface(
+    fn=text_to_speech,
+    inputs="text",
+    outputs="audio",
+    title="Vietnamese Text-to-Speech",
+    description="Enter Vietnamese text to convert to speech using FastSpeech 2 model."
+)
+
+iface.launch()