import os import re import random from scipy.io.wavfile import write from scipy.io.wavfile import read import numpy as np import gradio as gr import yt_dlp import subprocess mdxnet_models = [ 'UVR-MDX-NET-Inst_full_292.onnx', 'UVR-MDX-NET_Inst_187_beta.onnx', 'UVR-MDX-NET_Inst_82_beta.onnx', 'UVR-MDX-NET_Inst_90_beta.onnx', 'UVR-MDX-NET_Main_340.onnx', 'UVR-MDX-NET_Main_390.onnx', 'UVR-MDX-NET_Main_406.onnx', 'UVR-MDX-NET_Main_427.onnx', 'UVR-MDX-NET_Main_438.onnx', 'UVR-MDX-NET-Inst_HQ_1.onnx', 'UVR-MDX-NET-Inst_HQ_2.onnx', 'UVR-MDX-NET-Inst_HQ_3.onnx', 'UVR-MDX-NET-Inst_HQ_4.onnx', 'UVR_MDXNET_Main.onnx', 'UVR-MDX-NET-Inst_Main.onnx', 'UVR_MDXNET_1_9703.onnx', 'UVR_MDXNET_2_9682.onnx', 'UVR_MDXNET_3_9662.onnx', 'UVR-MDX-NET-Inst_1.onnx', 'UVR-MDX-NET-Inst_2.onnx', 'UVR-MDX-NET-Inst_3.onnx', 'UVR_MDXNET_KARA.onnx', 'UVR_MDXNET_KARA_2.onnx', 'UVR_MDXNET_9482.onnx', 'UVR-MDX-NET-Voc_FT.onnx', 'Kim_Vocal_1.onnx', 'Kim_Vocal_2.onnx', 'Kim_Inst.onnx', 'Reverb_HQ_By_FoxJoy.onnx', 'UVR-MDX-NET_Crowd_HQ_1.onnx', 'kuielab_a_vocals.onnx', 'kuielab_a_other.onnx', 'kuielab_a_bass.onnx', 'kuielab_a_drums.onnx', 'kuielab_b_vocals.onnx', 'kuielab_b_other.onnx', 'kuielab_b_bass.onnx', 'kuielab_b_drums.onnx', ] output_format = [ 'wav', 'flac', 'mp3', ] mdxnet_overlap_values = [ '0.25', '0.5', '0.75', '0.99', ] 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' sample_rate, audio_data = read(file_path) audio_array = np.asarray(audio_data, dtype=np.int16) return sample_rate, audio_array def mdxnet_separator(mdxnet_audio, mdxnet_model, mdxnet_output_format, mdxnet_segment_size, mdxnet_overlap, mdxnet_denoise): files_list = [] files_list.clear() directory = "./outputs" random_id = str(random.randint(10000, 99999)) pattern = f"{random_id}" os.makedirs("outputs", exist_ok=True) write(f'{random_id}.wav', mdxnet_audio[0], mdxnet_audio[1]) prompt = f"audio-separator {random_id}.wav --model_filename {mdxnet_model} --output_dir=./outputs --output_format={mdxnet_output_format} --normalization=0.9 --mdx_segment_size={mdxnet_segment_size} --mdx_overlap={mdxnet_overlap}" if mdxnet_denoise: prompt += " --mdx_enable_denoise" os.system(prompt) for file in os.listdir(directory): if re.search(pattern, file): files_list.append(os.path.join(directory, file)) stem1_file = files_list[0] stem2_file = files_list[1] return stem1_file, stem2_file def mdxnet_batch(path_input, path_output, model, output_format, overlap, segment_size, denoise): found_files = [] logs = [] logs.clear() extensions = (".mp3", ".wav", ".flac") for audio_files in os.listdir(path_input): if audio_files.endswith(extensions): found_files.append(audio_files) total_files = len(found_files) if total_files == 0: logs.append("No valid audio files.") yield "\n".join(logs) else: logs.append(f"{total_files} audio files found") found_files.sort() for audio_files in found_files: file_path = os.path.join(path_input, audio_files) prompt = ["audio-separator", file_path, "-m", f"{model}", f"--output_dir={path_output}", f"--output_format={output_format}", "--normalization=0.9", f"--mdx_overlap={overlap}", f"--mdx_segment_size={segment_size}"] if denoise: prompt.append("--mdx_enable_denoise") logs.append(f"Processing file: {audio_files}") yield "\n".join(logs) subprocess.run(prompt) logs.append(f"File: {audio_files} processed!") yield "\n".join(logs) with gr.Blocks(theme="Blane187/fuchsia", title="🎵 UVR5 MDX 🎵") as app: gr.Markdown("

🎵 UVR MDX 🎵

") gr.Markdown("If you liked this HF Space you can give me a ❤️") gr.Markdown("Try UVR5 UI using Colab [here](https://colab.research.google.com/github/Eddycrack864/UVR5-UI/blob/main/UVR_UI.ipynb)") with gr.Tabs(): with gr.TabItem("MDX-NET"): with gr.Row(): mdxnet_model = gr.Dropdown( label = "Select the Model", choices = mdxnet_models, interactive = True ) with gr.Row(): mdxnet_output_format = gr.Dropdown( label = "Select the Output Format", choices = output_format, interactive = True ) with gr.Row(): mdxnet_segment_size = gr.Slider( minimum = 32, maximum = 4000, step = 32, label = "Segment Size", info = "Larger consumes more resources, but may give better results.", value = 256, interactive = True ) with gr.Row(): mdxnet_overlap = gr.Dropdown( label = "Overlap", choices = mdxnet_overlap_values, value = mdxnet_overlap_values[0], interactive = True ) mdxnet_denoise = gr.Checkbox( label = "Denoise", info = "Enable denoising during separation.", value = True, interactive = True ) with gr.Row(): mdxnet_audio = gr.Audio( label = "Input Audio", type = "numpy", interactive = True ) with gr.Accordion("Separation by Link", open = False): with gr.Row(): mdxnet_link = gr.Textbox( label = "Link", placeholder = "Paste the link here", interactive = True ) with gr.Row(): gr.Markdown("You can paste the link to the video/audio from many sites, check the complete list [here](https://github.com/yt-dlp/yt-dlp/blob/master/supportedsites.md)") with gr.Row(): mdxnet_download_button = gr.Button( "Download!", variant = "primary" ) mdxnet_download_button.click(download_audio, [mdxnet_link], [mdxnet_audio]) with gr.Accordion("Batch Separation", open = False): with gr.Row(): mdxnet_input_path = gr.Textbox( label = "Input Path", placeholder = "Place the input path here", interactive = True ) mdxnet_output_path = gr.Textbox( label = "Output Path", placeholder = "Place the output path here", interactive = True ) with gr.Row(): mdxnet_bath_button = gr.Button("Separate!", variant = "primary") with gr.Row(): mdxnet_info = gr.Textbox( label = "Output Information", interactive = False ) mdxnet_bath_button.click(mdxnet_batch, [mdxnet_input_path, mdxnet_output_path, mdxnet_model, mdxnet_output_format, mdxnet_overlap, mdxnet_segment_size, mdxnet_denoise], [mdxnet_info]) with gr.Row(): mdxnet_button = gr.Button("Separate!", variant = "primary") with gr.Row(): mdxnet_stem1 = gr.Audio( show_download_button = True, interactive = False, label = "instrumental", type = "filepath" ) mdxnet_stem2 = gr.Audio( show_download_button = True, interactive = False, label = "vocal", type = "filepath" ) mdxnet_button.click(mdxnet_separator, [mdxnet_audio, mdxnet_model, mdxnet_output_format, mdxnet_segment_size, mdxnet_overlap, mdxnet_denoise], [mdxnet_stem1, mdxnet_stem2]) with gr.TabItem("Credits"): gr.Markdown( """ UVR5 UI created by **[Eddycrack 864](https://github.com/Eddycrack864).** Join **[AI HUB](https://discord.gg/aihub)** community. * python-audio-separator by [beveradb](https://github.com/beveradb). * Special thanks to [Ilaria](https://github.com/TheStingerX) for hosting this space and help. * Thanks to [Mikus](https://github.com/cappuch) for the help with the code. * Thanks to [Nick088](https://huggingface.co/Nick088) for the help to fix roformers. * Thanks to [yt_dlp](https://github.com/yt-dlp/yt-dlp) devs. * Separation by link source code and improvements by [Blane187](https://huggingface.co/Blane187). You can donate to the original UVR5 project here: [!["Buy Me A Coffee"](https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png)](https://www.buymeacoffee.com/uvr5) """ ) app.launch(share=True, debug=True)