Update app.py

app.py

@@ -9,23 +9,27 @@ MODEL_INFO = [
     ["vits-espeak-57000", "checkpoint_57000.pth", "config.json", "mhrahmani/persian-tts-vits-0"],
 ]
 
-# Extract model names from MODEL_INFO
-MODEL_NAMES = [info[0] for info in MODEL_INFO]
+# # Extract model names from MODEL_INFO
+# MODEL_NAMES = [info[0] for info in MODEL_INFO]
+
+MODEL_NAMES = [
+    "vits checkoint 57000",
+    # Add other model names similarly...
+]
+
 
 MAX_TXT_LEN = 400
 TOKEN = os.getenv('HUGGING_FACE_HUB_TOKEN')
 
-# Dictionary to keep synthesizers
-synthesizers = {}
-
-# Download files and create synthesizers
+# Download models
 for model_name, model_file, config_file, repo_name in MODEL_INFO:
+    os.makedirs(model_name, exist_ok=True)
     print(f"|> Downloading: {model_name}")
+    
+    # Use hf_hub_download to download models from private Hugging Face repositories
+    hf_hub_download(repo_id=repo_name, filename=model_file, cache_dir=model_name, use_auth_token=TOKEN)
+    hf_hub_download(repo_id=repo_name, filename=config_file, cache_dir=model_name, use_auth_token=TOKEN)
 
-    model_file_path = hf_hub_download(repo_id=repo_name, filename=model_file, use_auth_token=TOKEN)
-    config_file_path = hf_hub_download(repo_id=repo_name, filename=config_file, use_auth_token=TOKEN)
-
-    synthesizers[model_name] = Synthesizer(model_file_path, config_file_path)
 
 def synthesize(text: str, model_name: str) -> str:
     """Synthesize speech using the selected model."""
@@ -33,10 +37,10 @@ def synthesize(text: str, model_name: str) -> str:
         text = text[:MAX_TXT_LEN]
         print(f"Input text was cut off as it exceeded the {MAX_TXT_LEN} character limit.")
     
-    synthesizer = synthesizers[model_name]
+    synthesizer = Synthesizer(f"{model_name}/{model_file}", f"{model_name}/{config_file}")
     if synthesizer is None:
         raise NameError("Model not found")
-
+    
     wavs = synthesizer.tts(text)
     
     with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as fp: