Upload openvoice_app.py with huggingface_hub

openvoice_app.py

@@ -3,19 +3,31 @@ import torch
 import argparse
 import gradio as gr
 import requests
-import langid
 from openvoice import se_extractor
 from openvoice.api import BaseSpeakerTTS, ToneColorConverter
 from dotenv import load_dotenv
 from openai import OpenAI
 from elevenlabs.client import ElevenLabs
-from elevenlabs import play,save
+from elevenlabs import play, save
+from flask import Flask
+from flask_limiter import Limiter
+from flask_limiter.util import get_remote_address
+
+# Load environment variables
 load_dotenv()
 
+# Initialize Flask app
+app = Flask(__name__)
+
+# Setup Limiter for rate limiting and quota management based on IP address
+limiter = Limiter(get_remote_address, app=app, default_limits=["1 per 10 minutes"])
+
 # Argument parsing
 parser = argparse.ArgumentParser()
 parser.add_argument("--share", action='store_true', default=False, help="make link public")
 args = parser.parse_args()
+
+# Initialize ElevenLabs client
 client = ElevenLabs(api_key=os.environ.get("ELEVENLABS_API_KEY"))
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 output_dir = 'outputs'
@@ -23,6 +35,7 @@ os.makedirs(output_dir, exist_ok=True)
 
 api_key = os.environ.get("ELEVENLABS_API_KEY")
 supported_languages = ['zh', 'en']
+
 # Function to get all voices
 def get_voices(api_key):
     url = "https://api.elevenlabs.io/v1/voices"
@@ -37,7 +50,8 @@ def delete_voice(api_key, voice_id):
     response = requests.request("DELETE", url, headers=headers)
     return response.status_code, response.text
 
-
+# Predict function with rate limiting based on IP address
+@limiter.limit("1 per 10 minutes")
 def predict(prompt, style, audio_file_pth):
     text_hint = ''
     if len(prompt) < 2:
@@ -53,7 +67,7 @@ def predict(prompt, style, audio_file_pth):
         description="A trial voice model for testing",
         files=[audio_file_pth],
     )
-    #text should be prompt
+    # Generate audio from text
     audio = client.generate(text=prompt, voice=voice)
     save(audio, f'{output_dir}/output.wav')
     
@@ -84,7 +98,7 @@ with gr.Blocks(gr.themes.Glass()) as demo:
             style_gr = gr.Dropdown(
                 label="Style",
                 choices=['default', 'whispering', 'cheerful', 'terrified', 'angry', 'sad', 'friendly'],
-                info="Please upload a reference audio file that is atleast 1 minute long. For best results, ensure the audio is clear. You can use Adobe Podcast Enhance(https://podcast.adobe.com/enhance) to improve the audio quality before uploading.",
+                info="Please upload a reference audio file that is at least 1 minute long. For best results, ensure the audio is clear. You can use Adobe Podcast Enhance(https://podcast.adobe.com/enhance) to improve the audio quality before uploading.",
                 max_choices=1,
                 value="default",
             )
@@ -100,11 +114,15 @@ with gr.Blocks(gr.themes.Glass()) as demo:
             audio_gr = gr.Audio(label="Synthesised Audio", autoplay=True)
             ref_audio_gr = gr.Audio(label="Reference Audio Used")
 
-            tts_button.click(predict, [input_text_gr, style_gr, ref_gr], outputs=[out_text_gr, audio_gr, ref_audio_gr])
+            def handle_click(prompt, style, audio_file_pth):
+                ip = request.remote_addr
+                return predict(prompt, style, audio_file_pth, ip)
+            
+            tts_button.click(handle_click,
+                             [input_text_gr, style_gr, ref_gr], outputs=[out_text_gr, audio_gr, ref_audio_gr])
 
 demo.queue()
 demo.launch(debug=True, show_api=False, share=args.share)
 
 # Hide Gradio footer
 css = "footer {visibility: hidden}"
-