Update app.py

app.py

@@ -1,12 +1,28 @@
+import os
+
+import gradio as gr
+import numpy as np
+import soundfile as sf
+import torch
+
+os.system("git clone --branch v2.3 https://github.com/DigitalPhonetics/IMS-Toucan.git toucan_codebase")
+os.system("mv toucan_codebase/* .")
+
+from run_model_downloader import download_models
+
+download_models()
+
+
+
 import gradio as gr
 import numpy as np
 import torch
 import math
 import os
-from Preprocessing.ArticulatoryCombinedTextFrontend import ArticulatoryCombinedTextFrontend
+from Preprocessing.TextFrontend import ArticulatoryCombinedTextFrontend
 from TrainingInterfaces.Text_to_Spectrogram.AutoAligner.Aligner import Aligner
 from TrainingInterfaces.Text_to_Spectrogram.FastSpeech2.DurationCalculator import DurationCalculator
-from run_utterance_cloner import UtteranceCloner
+from InferenceInterfaces.UtteranceCloner import UtteranceCloner
 
 def float2pcm(sig, dtype='int16'):
     """
@@ -28,7 +44,7 @@ class TTS_Interface:
 
     def __init__(self):
         self.device = "cuda" if torch.cuda.is_available() else "cpu"
-        self.utterance_cloner = UtteranceCloner(device=self.device)
+        self.utterance_cloner = UtteranceCloner(model_id="Meta", device=self.device)
         self.utterance_cloner.tts.set_language("de")
         self.acoustic_model = Aligner()
         self.acoustic_model.load_state_dict(torch.load("Models/Aligner/aligner.pt", map_location='cpu')["asr_model"])