Update app.py

app.py

@@ -5,7 +5,7 @@ import gradio as gr
 import numpy as np
 import tempfile
 from einops import rearrange
-from vocos import Vocos
+#from vocos import Vocos
 from pydub import AudioSegment, silence
 from model import CFM, UNetT, DiT, MMDiT
 from cached_path import cached_path
@@ -52,8 +52,8 @@ pipe = pipeline(
     torch_dtype=torch.float16,
     device=device,
 )
-vocos = Vocos.from_pretrained("charactr/vocos-mel-24khz")
-
+#vocos = Vocos.from_pretrained("charactr/vocos-mel-24khz")
+vocos = load_vocoder()
 # --------------------- Settings -------------------- #
 
 target_sample_rate = 24000
@@ -74,7 +74,7 @@ tts_model_choice = DEFAULT_TTS_MODEL
 
 # load models
 
-vocoder = load_vocoder()
+
 
 
 def load_f5tts(ckpt_path=str(cached_path("hf://SWivid/F5-TTS/F5TTS_Base/model_1200000.safetensors"))):