Update module.py

module.py

@@ -15,11 +15,149 @@ import tempfile
 import anyio
 from pathlib import Path
 from lib.language_tts import language_dict
-import os
-import zipfile
 import shutil
-import urllib.request
-import gdown
-import subprocess
 import time
-from argparse import ArgumentParser
+from argparse import ArgumentParser
+from download_model import download_online_model
+
+main_dir = Path().resolve()
+print(main_dir)
+
+os.chdir(main_dir)
+models_dir = main_dir / "rvc_models"
+audio_separat_dir = main_dir / "audio_input"
+AUDIO_DIR = main_dir / 'audio_input'
+
+
+# Function to list all folders in the models directory
+def get_folders():
+    if models_dir.exists() and models_dir.is_dir():
+        return [folder.name for folder in models_dir.iterdir() if folder.is_dir()]
+    return []
+
+
+# Function to refresh and return the list of folders
+def refresh_folders():
+    return gr.Dropdown.update(choices=get_folders())
+
+
+# Function to get the list of audio files in the specified directory
+def get_audio_files():
+    if not os.path.exists(AUDIO_DIR):
+        os.makedirs(AUDIO_DIR)
+    return [f for f in os.listdir(AUDIO_DIR) if f.lower().endswith(('.mp3', '.wav', '.flac', '.ogg', '.aac'))]
+
+
+# Function to return the full path of audio files for playback
+def load_audio_files():
+    audio_files = get_audio_files()
+    return [os.path.join(AUDIO_DIR, f) for f in audio_files]
+
+
+def refresh_audio_list():
+    audio_files = load_audio_files()
+    return gr.Dropdown.update(choices=audio_files)
+
+
+def download_audio(url):
+    ydl_opts = {
+        'format': 'bestaudio/best',
+        'outtmpl': 'ytdl/%(title)s.%(ext)s',
+        'postprocessors': [{
+            'key': 'FFmpegExtractAudio',
+            'preferredcodec': 'wav',
+            'preferredquality': '192',
+        }],
+    }
+
+    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+        info_dict = ydl.extract_info(url, download=True)
+        file_path = ydl.prepare_filename(info_dict).rsplit('.', 1)[0] + '.wav'
+        return file_path
+
+
+async def text_to_speech_edge(text, language_code):
+    voice = language_dict.get(language_code, "default_voice")
+    communicate = edge_tts.Communicate(text, voice)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
+        tmp_path = tmp_file.name
+        await communicate.save(tmp_path)
+    return tmp_path
+
+
+if __name__ == '__main__':
+    parser = ArgumentParser()
+    parser.add_argument("--share", action="store_true", dest="share_enabled", default=False)
+    parser.add_argument("--listen", action="store_true", default=False)
+    parser.add_argument('--listen-host', type=str)
+    parser.add_argument('--listen-port', type=int)
+    args = parser.parse_args()
+
+# Gradio Interface
+with gr.Blocks(title="Hex RVC", theme=gr.themes.Base(primary_hue="red", secondary_hue="pink")) as app:
+    gr.Markdown("# Hex RVC")
+    gr.Markdown("Join [AIHub](https://discord.gg/aihub) to get the RVC model!")
+    
+    with gr.Tab("Inference"):
+        with gr.Row():
+            MODEL_NAME = gr.Dropdown(
+                label="Select a Model",
+                choices=get_folders(),
+                interactive=True
+            )
+            SOUND_PATH = gr.Dropdown(
+                choices=load_audio_files(),
+                label="Select an audio file",
+                interactive=True
+            )
+            upload_audio = gr.Audio(label="Upload Audio", type='filepath')
+
+        with gr.Accordion("Hex TTS"):
+            input_text = gr.Textbox(lines=5, label="Input Text")
+            language = gr.Dropdown(choices=list(language_dict.keys()), label="Choose the Voice Model")
+            tts_convert = gr.Button("Convert")
+            tts_output = gr.Audio(label="Generated TTS Audio", type='filepath')
+            
+            tts_convert.click(
+                fn=text_to_speech_edge, 
+                inputs=[input_text, language], 
+                outputs=tts_output
+            )
+
+        output_audio = gr.Audio(label="Generated Audio", type='filepath')
+        with gr.Row():
+            refresh_btn = gr.Button("Refresh")
+            run_button = gr.Button("Convert")
+
+        refresh_btn.click(
+            lambda: (refresh_audio_list(), refresh_folders()),
+            outputs=[SOUND_PATH, MODEL_NAME]
+        )
+
+    with gr.Tab("Download RVC Model"):
+        url = gr.Textbox(label="Your Model URL")
+        dirname = gr.Textbox(label="Your Model Name")
+        download_button = gr.Button("Download Model")
+        download_output = gr.Textbox(label="Download Status")
+
+        download_button.click(
+            download_online_model,
+            inputs=[url, dirname],
+            outputs=download_output
+        )
+
+    with gr.Tab("UVR5 (Demo)"):
+        input_audio = gr.Audio(type="filepath", label="Upload Audio")
+        roformer_link = gr.Textbox(label="Audio Link")
+        roformer_download_button = gr.Button("Download")
+        
+        separate_button = gr.Button("Separate Audio")
+        separation_output = gr.Textbox(label="Separation Output Path")
+
+        roformer_download_button.click(download_audio, inputs=[roformer_link], outputs=[input_audio])
+
+app.launch(
+    share=args.share_enabled,
+    server_name=None if not args.listen else (args.listen_host or '0.0.0.0'),
+    server_port=args.listen_port,
+)