Update app.py

app.py

@@ -6,30 +6,26 @@ from huggingface_hub import hf_hub_download
 
 # Define constants
 MODEL_INFO = [
-    # ["Model Name", "Model File", "Config File", "Hub URL"]
     ["vits-espeak-57000", "checkpoint_57000.pth", "config.json", "mhrahmani/persian-tts-vits-0"],
-    # Add other models similarly...
 ]
 
 # Extract model names from MODEL_INFO
 MODEL_NAMES = [info[0] for info in MODEL_INFO]
 
 MAX_TXT_LEN = 400
-TOKEN = os.environ.get('HUGGING_FACE_HUB_TOKEN')  # Replace with the environment variable containing your token, if different
+TOKEN = os.getenv('HUGGING_FACE_HUB_TOKEN')
 
+# Dictionary to keep synthesizers
+synthesizers = {}
 
-# Verify if the files are downloaded correctly
+# Download files and create synthesizers
 for model_name, model_file, config_file, repo_name in MODEL_INFO:
-    # os.makedirs(model_name, exist_ok=True)
     print(f"|> Downloading: {model_name}")
-    
+
     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)
-    
-    # # Check if the files exist after download
-    # if not os.path.exists(model_file_path) or not os.path.exists(config_file_path):
-    #     raise FileNotFoundError(f"Failed to download files for {model_name}. Please check the repository and file names.")
 
+    synthesizers[model_name] = Synthesizer(model_file_path, config_file_path)
 
 def synthesize(text: str, model_name: str) -> str:
     """Synthesize speech using the selected model."""
@@ -37,20 +33,17 @@ 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.")
     
-    # Extract model_file and config_file based on the model_name
-    model_file, config_file = next((model_file, config_file) for name, model_file, config_file, _ in MODEL_INFO if name == model_name)
-    
-    synthesizer = Synthesizer(model_file_path, config_file_path)
+    synthesizer = synthesizers[model_name]
     if synthesizer is None:
         raise NameError("Model not found")
-    
+
     wavs = synthesizer.tts(text)
     
     with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as fp:
         synthesizer.save_wav(wavs, fp)
         return fp.name
 
-# Define Gradio interface
+
 iface = gr.Interface(
     fn=synthesize,
     inputs=[
@@ -59,12 +52,10 @@ iface = gr.Interface(
     ],
     outputs=gr.Audio(label="Output", type='filepath'),
     examples=[["زین همرهان سست عناصر، دلم گرفت.", MODEL_NAMES[0]]],
-    title='persian tts playground',
-    description="Persian text to speech model demo",  # Add the required description here.
+    title='Persian TTS Playground',
+    description="Persian text to speech model demo",
     article="",
     live=False
 )
 
-# Launch the interface
 iface.launch(share=False)
-