Create app.py

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+import torch
+import soundfile as sf
+from inference import TTSInference
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+tts = TTSInference(
+    model_path="model.pt",
+    tokenizer_path="tts_tokenizer.model",
+    device=device
+)
+
+def synthesize(text):
+    audio = tts.synthesize(text)
+    sf.write("output.wav", audio.numpy(), 22050)
+    return "output.wav"
+
+iface = gr.Interface(
+    fn=synthesize,
+    inputs=gr.Textbox(label="Enter Text"),
+    outputs=gr.Audio(type="filepath"),
+    title="Realtime Multilingual TTS",
+    description="Frame-Level Positional Encoding Optimized for Conversations"
+)
+
+iface.launch()