Initial commit

app.py

@@ -1,7 +1,7 @@
 import random
 import numpy as np
 import torch
-from chatterbox.src.chatterbox.tts import ChatterboxTTS
+from echobox.src.echobox.tts import EchoBoxTTS
 import gradio as gr
 import spaces
 
@@ -12,13 +12,13 @@ print(f"🚀 Running on device: {DEVICE}")
 MODEL = None
 
 def get_or_load_model():
-    """Loads the ChatterboxTTS model if it hasn't been loaded already,
+    """Loads the EchoBoxTTS model if it hasn't been loaded already,
     and ensures it's on the correct device."""
     global MODEL
     if MODEL is None:
         print("Model not loaded, initializing...")
         try:
-            MODEL = ChatterboxTTS.from_pretrained(DEVICE)
+            MODEL = EchoBoxTTS.from_pretrained(DEVICE)
             if hasattr(MODEL, 'to') and str(MODEL.device) != DEVICE:
                 MODEL.to(DEVICE)
             print(f"Model loaded successfully. Internal device: {getattr(MODEL, 'device', 'N/A')}")
@@ -52,7 +52,7 @@ def generate_tts_audio(
     cfgw_input: float
 ) -> tuple[int, np.ndarray]:
     """
-    Generates TTS audio using the ChatterboxTTS model.
+    Generates TTS audio using the EchoboxTTS model.
 
     Args:
         text_input: The text to synthesize (max 300 characters).
@@ -87,7 +87,7 @@ def generate_tts_audio(
 with gr.Blocks() as demo:
     gr.Markdown(
         """
-        # Chatterbox TTS Demo
+        # EchoBox TTS Demo
         Generate high-quality speech from text with reference audio styling.
         """
     )