Create app.py

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+import torch
+from nemo.collections.tts.models import FastPitchModel
+from nemo.collections.tts.models import HifiGanModel
+
+# 🔹 Load pretrained models from NeMo
+fastpitch = FastPitchModel.from_pretrained("nvidia/tts_en_fastpitch")
+hifigan = HifiGanModel.from_pretrained("nvidia/tts_hifigan")
+
+# 🔹 TTS function
+def tts(text):
+    # Convert text → mel spectrogram
+    with torch.no_grad():
+        spectrogram = fastpitch.parse(text)
+        audio = hifigan.convert_spectrogram_to_audio(spectrogram)
+    return (22050, audio.cpu().numpy())
+
+# 🔹 Gradio UI
+iface = gr.Interface(
+    fn=tts,
+    inputs=gr.Textbox(label="Enter text"),
+    outputs=gr.Audio(label="Generated Speech"),
+    title="FastPitch + HiFiGAN (NeMo TTS)",
+    description="Enter text and get speech synthesized using NVIDIA NeMo FastPitch and HiFiGAN."
+)
+
+iface.launch()