Update app.py

app.py

@@ -0,0 +1,70 @@
+import os
+import tempfile
+import gradio as gr
+from TTS.utils.synthesizer import Synthesizer
+from huggingface_hub import hf_hub_download
+
+# Define constants
+MODEL_INFO = [
+    ["vits-multispeaker-495586", "best_model_495586.pth", "config.json", "saillab/vits_multi_cv_15_validated_dataset/resolve/main/","speakers.pth"],
+]
+
+# # Extract model names from MODEL_INFO
+# MODEL_NAMES = [info[0] for info in MODEL_INFO]
+
+MODEL_NAMES = [
+    "vits-multispeaker-495586",
+    # Add other model names similarly...
+]
+
+MAX_TXT_LEN = 400
+TOKEN = os.getenv('HUGGING_FACE_HUB_TOKEN')
+
+# # 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, use_auth_token=TOKEN)
+#     hf_hub_download(repo_id=repo_name, filename=config_file, use_auth_token=TOKEN)
+
+repo_name = "saillab/vits_multi_cv_15_validated_dataset"
+filename = "best_model_495586.pth"
+
+model_file = hf_hub_download(repo_name, filename, use_auth_token=TOKEN)
+config_file = hf_hub_download(repo_name, "config.json", use_auth_token=TOKEN)
+
+
+def synthesize(text: str, model_name: str) -> str:
+    """Synthesize speech using the selected model."""
+    if len(text) > MAX_TXT_LEN:
+        text = text[:MAX_TXT_LEN]
+        print(f"Input text was cut off as it exceeded the {MAX_TXT_LEN} character limit.")
+    
+    synthesizer = Synthesizer(model_file, config_file)
+    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
+
+
+iface = gr.Interface(
+    fn=synthesize,
+    inputs=[
+        gr.Textbox(label="Enter Text to Synthesize:", value="زین همرهان سست عناصر، دلم گرفت."),
+        gr.Radio(label="Pick a Model", choices=MODEL_NAMES, value=MODEL_NAMES[0]),
+    ],
+    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",
+    article="",
+    live=False
+)
+
+iface.launch()