from original import * import shutil, glob from easyfuncs import download_from_url, CachedModels os.makedirs("dataset",exist_ok=True) model_library = CachedModels() from typing import Iterable import gradio as gr os.system("python tools/download_models.py") # -> dummy extra # gr.themes.builder() from gradio.themes.base import Base from gradio.themes.utils import colors, fonts, sizes import time # Applio Theme class Applio(Base): def __init__( self, *, primary_hue: colors.Color | str = colors.neutral, secondary_hue: colors.Color | str = colors.neutral, neutral_hue: colors.Color | str = colors.neutral, spacing_size: sizes.Size | str = sizes.spacing_md, radius_size: sizes.Size | str = sizes.radius_md, text_size: sizes.Size | str = sizes.text_lg, font: fonts.Font | str | Iterable[fonts.Font | str] = ( "Syne V", fonts.GoogleFont("Syne"), "ui-sans-serif", "system-ui", ), font_mono: fonts.Font | str | Iterable[fonts.Font | str] = ( "ui-monospace", fonts.GoogleFont("Nunito Sans"), ), ): super().__init__( primary_hue=primary_hue, secondary_hue=secondary_hue, neutral_hue=neutral_hue, spacing_size=spacing_size, radius_size=radius_size, text_size=text_size, font=font, font_mono=font_mono, ) self.name = ("Applio",) self.secondary_100 = ("#dbeafe",) self.secondary_200 = ("#bfdbfe",) self.secondary_300 = ("#93c5fd",) self.secondary_400 = ("#60a5fa",) self.secondary_50 = ("#eff6ff",) self.secondary_500 = ("#3b82f6",) self.secondary_600 = ("#2563eb",) self.secondary_700 = ("#1d4ed8",) self.secondary_800 = ("#1e40af",) self.secondary_900 = ("#1e3a8a",) self.secondary_950 = ("#1d3660",) super().set( # Blaise background_fill_primary="#110F0F", background_fill_primary_dark="#110F0F", background_fill_secondary="#110F0F", background_fill_secondary_dark="#110F0F", block_background_fill="*neutral_800", block_background_fill_dark="*neutral_800", block_border_color="*border_color_primary", block_border_color_dark="*border_color_primary", block_border_width="1px", block_border_width_dark="1px", block_info_text_color="*body_text_color_subdued", block_info_text_color_dark="*body_text_color_subdued", block_info_text_size="*text_sm", block_info_text_weight="400", block_label_background_fill="*background_fill_primary", block_label_background_fill_dark="*background_fill_secondary", block_label_border_color="*border_color_primary", block_label_border_color_dark="*border_color_primary", block_label_border_width="1px", block_label_border_width_dark="1px", block_label_margin="0", block_label_padding="*spacing_sm *spacing_lg", block_label_radius="calc(*radius_lg - 1px) 0 calc(*radius_lg - 1px) 0", block_label_right_radius="0 calc(*radius_lg - 1px) 0 calc(*radius_lg - 1px)", block_label_shadow="*block_shadow", block_label_text_color="*#110F0F", block_label_text_color_dark="*#110F0F", block_label_text_weight="400", block_padding="*spacing_xl", block_radius="*radius_md", block_shadow="none", block_shadow_dark="none", block_title_background_fill="rgb(255,255,255)", block_title_background_fill_dark="rgb(255,255,255)", block_title_border_color="none", block_title_border_color_dark="none", block_title_border_width="0px", block_title_padding="*block_label_padding", block_title_radius="*block_label_radius", block_title_text_color="#110F0F", block_title_text_color_dark="#110F0F", block_title_text_size="*text_md", block_title_text_weight="600", body_background_fill="#110F0F", body_background_fill_dark="#110F0F", body_text_color="white", body_text_color_dark="white", body_text_color_subdued="*neutral_400", body_text_color_subdued_dark="*neutral_400", body_text_size="*text_md", body_text_weight="400", border_color_accent="*neutral_600", border_color_accent_dark="*neutral_600", border_color_primary="*neutral_800", border_color_primary_dark="*neutral_800", button_border_width="*input_border_width", button_border_width_dark="*input_border_width", button_cancel_background_fill="*button_secondary_background_fill", button_cancel_background_fill_dark="*button_secondary_background_fill", button_cancel_background_fill_hover="*button_cancel_background_fill", button_cancel_background_fill_hover_dark="*button_cancel_background_fill", button_cancel_border_color="*button_secondary_border_color", button_cancel_border_color_dark="*button_secondary_border_color", button_cancel_border_color_hover="*button_cancel_border_color", button_cancel_border_color_hover_dark="*button_cancel_border_color", button_cancel_text_color="#110F0F", button_cancel_text_color_dark="#110F0F", button_cancel_text_color_hover="#110F0F", button_cancel_text_color_hover_dark="#110F0F", button_large_padding="*spacing_lg calc(2 * *spacing_lg)", button_large_radius="*radius_lg", button_large_text_size="*text_lg", button_large_text_weight="600", button_primary_background_fill="*primary_600", button_primary_background_fill_dark="*primary_600", button_primary_background_fill_hover="*primary_500", button_primary_background_fill_hover_dark="*primary_500", button_primary_border_color="*primary_500", button_primary_border_color_dark="*primary_500", button_primary_border_color_hover="*primary_400", button_primary_border_color_hover_dark="*primary_400", button_primary_text_color="white", button_primary_text_color_dark="white", button_primary_text_color_hover="#110F0F", button_primary_text_color_hover_dark="#110F0F", button_secondary_background_fill="transparent", button_secondary_background_fill_dark="transparent", button_secondary_background_fill_hover="*neutral_800", button_secondary_background_fill_hover_dark="*neutral_800", button_secondary_border_color="*neutral_700", button_secondary_border_color_dark="*neutral_700", button_secondary_border_color_hover="*neutral_600", button_secondary_border_color_hover_dark="*neutral_600", button_secondary_text_color="white", button_secondary_text_color_dark="white", button_secondary_text_color_hover="*button_secondary_text_color", button_secondary_text_color_hover_dark="*button_secondary_text_color", button_shadow="none", button_shadow_active="*shadow_inset", button_shadow_hover="none", button_small_padding="*spacing_sm calc(2 * *spacing_sm)", button_small_radius="*radius_lg", button_small_text_size="*text_md", button_small_text_weight="400", button_transition="0.3s ease all", checkbox_background_color="*neutral_700", checkbox_background_color_dark="*neutral_700", checkbox_background_color_focus="*checkbox_background_color", checkbox_background_color_focus_dark="*checkbox_background_color", checkbox_background_color_hover="*checkbox_background_color", checkbox_background_color_hover_dark="*checkbox_background_color", checkbox_background_color_selected="*secondary_600", checkbox_background_color_selected_dark="*secondary_600", checkbox_border_color="*neutral_700", checkbox_border_color_dark="*neutral_700", checkbox_border_color_focus="*secondary_500", checkbox_border_color_focus_dark="*secondary_500", checkbox_border_color_hover="*neutral_600", checkbox_border_color_hover_dark="*neutral_600", checkbox_border_color_selected="*secondary_600", checkbox_border_color_selected_dark="*secondary_600", checkbox_border_radius="*radius_sm", checkbox_border_width="*input_border_width", checkbox_border_width_dark="*input_border_width", checkbox_check="url(\"data:image/svg+xml,%3csvg viewBox='0 0 16 16' fill='white' xmlns='http://www.w3.org/2000/svg'%3e%3cpath d='M12.207 4.793a1 1 0 010 1.414l-5 5a1 1 0 01-1.414 0l-2-2a1 1 0 011.414-1.414L6.5 9.086l4.293-4.293a1 1 0 011.414 0z'/%3e%3c/svg%3e\")", checkbox_label_background_fill="transparent", checkbox_label_background_fill_dark="transparent", checkbox_label_background_fill_hover="transparent", checkbox_label_background_fill_hover_dark="transparent", checkbox_label_background_fill_selected="transparent", checkbox_label_background_fill_selected_dark="transparent", checkbox_label_border_color="transparent", checkbox_label_border_color_dark="transparent", checkbox_label_border_color_hover="transparent", checkbox_label_border_color_hover_dark="transparent", checkbox_label_border_width="transparent", checkbox_label_border_width_dark="transparent", checkbox_label_gap="*spacing_lg", checkbox_label_padding="*spacing_md calc(2 * *spacing_md)", checkbox_label_shadow="none", checkbox_label_text_color="*body_text_color", checkbox_label_text_color_dark="*body_text_color", checkbox_label_text_color_selected="*checkbox_label_text_color", checkbox_label_text_color_selected_dark="*checkbox_label_text_color", checkbox_label_text_size="*text_md", checkbox_label_text_weight="400", checkbox_shadow="*input_shadow", color_accent="*primary_500", color_accent_soft="*primary_50", color_accent_soft_dark="*neutral_700", container_radius="*radius_xl", embed_radius="*radius_lg", error_background_fill="*background_fill_primary", error_background_fill_dark="*background_fill_primary", error_border_color="*border_color_primary", error_border_color_dark="*border_color_primary", error_border_width="1px", error_border_width_dark="1px", error_text_color="#ef4444", error_text_color_dark="#ef4444", form_gap_width="0px", input_background_fill="*neutral_900", input_background_fill_dark="*neutral_900", input_background_fill_focus="*secondary_600", input_background_fill_focus_dark="*secondary_600", input_background_fill_hover="*input_background_fill", input_background_fill_hover_dark="*input_background_fill", input_border_color="*neutral_700", input_border_color_dark="*neutral_700", input_border_color_focus="*secondary_600", input_border_color_focus_dark="*primary_600", input_border_color_hover="*input_border_color", input_border_color_hover_dark="*input_border_color", input_border_width="1px", input_border_width_dark="1px", input_padding="*spacing_xl", input_placeholder_color="*neutral_500", input_placeholder_color_dark="*neutral_500", input_radius="*radius_lg", input_shadow="none", input_shadow_dark="none", input_shadow_focus="*input_shadow", input_shadow_focus_dark="*input_shadow", input_text_size="*text_md", input_text_weight="400", layout_gap="*spacing_xxl", link_text_color="*secondary_500", link_text_color_active="*secondary_500", link_text_color_active_dark="*secondary_500", link_text_color_dark="*secondary_500", link_text_color_hover="*secondary_400", link_text_color_hover_dark="*secondary_400", link_text_color_visited="*secondary_600", link_text_color_visited_dark="*secondary_600", loader_color="*color_accent", loader_color_dark="*color_accent", panel_background_fill="*background_fill_secondary", panel_background_fill_dark="*background_fill_secondary", panel_border_color="*border_color_primary", panel_border_color_dark="*border_color_primary", panel_border_width="1px", panel_border_width_dark="1px", prose_header_text_weight="600", prose_text_size="*text_md", prose_text_weight="400", radio_circle="url(\"data:image/svg+xml,%3csvg viewBox='0 0 16 16' fill='white' xmlns='http://www.w3.org/2000/svg'%3e%3ccircle cx='8' cy='8' r='3'/%3e%3c/svg%3e\")", section_header_text_size="*text_md", section_header_text_weight="400", shadow_drop="rgba(0,0,0,0.05) 0px 1px 2px 0px", shadow_drop_lg="0 1px 3px 0 rgb(0 0 0 / 0.1), 0 1px 2px -1px rgb(0 0 0 / 0.1)", shadow_inset="rgba(0,0,0,0.05) 0px 2px 4px 0px inset", shadow_spread="3px", shadow_spread_dark="1px", slider_color="#9E9E9E", slider_color_dark="#9E9E9E", stat_background_fill="*primary_500", stat_background_fill_dark="*primary_500", table_border_color="*neutral_700", table_border_color_dark="*neutral_700", table_even_background_fill="*neutral_950", table_even_background_fill_dark="*neutral_950", table_odd_background_fill="*neutral_900", table_odd_background_fill_dark="*neutral_900", table_radius="*radius_lg", table_row_focus="*color_accent_soft", table_row_focus_dark="*color_accent_soft", ) theme = Applio() with gr.Blocks(title="RVC V2",theme=theme) as app: with gr.Row(): gr.HTML("image") #toggle_dark = gr.Button(value="Toggle Dark") with gr.Tabs(): with gr.TabItem("Inference"): with gr.Row(): voice_model = gr.Dropdown(label="Model Voice", choices=sorted(names), value=lambda:sorted(names)[0] if len(sorted(names)) > 0 else '', interactive=True) refresh_button = gr.Button("Refresh", variant="primary") spk_item = gr.Slider( minimum=0, maximum=2333, step=1, label="Speaker ID", value=0, visible=False, interactive=True, ) vc_transform0 = gr.Number(label="Pitch",value=0) but0 = gr.Button(value="Convert", variant="primary") with gr.Row(): with gr.Column(): with gr.Row(): dropbox = gr.Audio(label="your audio here.") with gr.Column(): with gr.Accordion("Change Index", open=False): file_index2 = gr.Dropdown( label="Change Index", choices=sorted(index_paths), interactive=True, value=sorted(index_paths)[0] if len(sorted(index_paths)) > 0 else '' ) index_rate1 = gr.Slider( minimum=0, maximum=1, label="Index Strength", value=0.5, interactive=True, ) vc_output2 = gr.Audio(label="Output") with gr.Accordion("General Settings", open=False): f0method0 = gr.Radio( label="Method", choices=["pm", "harvest", "crepe", "rmvpe", "torchfcpe"] if config.dml == False else ["pm", "harvest", "rmvpe"], value="rmvpe", interactive=True, ) filter_radius0 = gr.Slider( minimum=0, maximum=7, label="Breathiness Reduction (Harvest only)", value=3, step=1, interactive=True, ) resample_sr0 = gr.Slider( minimum=0, maximum=48000, label="Resample", value=0, step=1, interactive=True, visible=False ) rms_mix_rate0 = gr.Slider( minimum=0, maximum=1, label="Volume Normalization", value=0, interactive=True, ) protect0 = gr.Slider( minimum=0, maximum=0.5, label="Breathiness Protection (0 is enabled, 0.5 is disabled)", value=0.33, step=0.01, interactive=True, ) if voice_model != None: vc.get_vc(voice_model.value,protect0,protect0) file_index1 = gr.Textbox( label="Index Path", interactive=True, visible=False#Not used here ) refresh_button.click( fn=change_choices, inputs=[], outputs=[voice_model, file_index2], api_name="infer_refresh", ) with gr.Row(): f0_file = gr.File(label="F0 Path", visible=False) with gr.Row(): vc_output1 = gr.Textbox(label="Information", placeholder="Welcome!",visible=False) but0.click( vc.vc_single, [ spk_item, dropbox, vc_transform0, f0_file, f0method0, file_index1, file_index2, index_rate1, filter_radius0, resample_sr0, rms_mix_rate0, protect0, ], [vc_output1, vc_output2], api_name="infer_convert", ) voice_model.change( fn=vc.get_vc, inputs=[voice_model, protect0, protect0], outputs=[spk_item, protect0, protect0, file_index2, file_index2], api_name="infer_change_voice", ) with gr.TabItem("Download Models"): with gr.Row(): url_input = gr.Textbox(label="URL to model", value="",placeholder="https://...", scale=6) name_output = gr.Textbox(label="Save as", value="",placeholder="MyModel",scale=2) url_download = gr.Button(value="Download Model",scale=2) url_download.click( inputs=[url_input,name_output], outputs=[url_input], fn=download_from_url, ) with gr.Row(): model_browser = gr.Dropdown(choices=list(model_library.models.keys()),label="OR Search Models (Quality UNKNOWN)",scale=5) download_from_browser = gr.Button(value="Get",scale=2) download_from_browser.click( inputs=[model_browser], outputs=[model_browser], fn=lambda model: download_from_url(model_library.models[model],model), ) #if warning: with gr.TabItem("read this"): gr.Markdown(f"This Spaces Using CPU dude\n may inference take long time\n and Train tab is disable :)") with gr.TabItem("Train", visible=False): with gr.Row(): with gr.Column(): training_name = gr.Textbox(label="Name your model", value="My-Voice",placeholder="My-Voice") np7 = gr.Slider( minimum=0, maximum=config.n_cpu, step=1, label="Number of CPU processes used to extract pitch features", value=int(np.ceil(config.n_cpu / 1.5)), interactive=True, ) sr2 = gr.Radio( label="Sampling Rate", choices=["40k", "32k"], value="32k", interactive=True, visible=False ) if_f0_3 = gr.Radio( label="Will your model be used for singing? If not, you can ignore this.", choices=[True, False], value=True, interactive=True, visible=False ) version19 = gr.Radio( label="Version", choices=["v1", "v2"], value="v2", interactive=True, visible=False, ) dataset_folder = gr.Textbox( label="dataset folder", value='dataset' ) easy_uploader = gr.Files(label="Drop your audio files here",file_types=['audio']) but1 = gr.Button("1. Process", variant="primary") info1 = gr.Textbox(label="Information", value="",visible=True) easy_uploader.upload(inputs=[dataset_folder],outputs=[],fn=lambda folder:os.makedirs(folder,exist_ok=True)) easy_uploader.upload( fn=lambda files,folder: [shutil.copy2(f.name,os.path.join(folder,os.path.split(f.name)[1])) for f in files] if folder != "" else gr.Warning('Please enter a folder name for your dataset'), inputs=[easy_uploader, dataset_folder], outputs=[]) gpus6 = gr.Textbox( label="Enter the GPU numbers to use separated by -, (e.g. 0-1-2)", value=gpus, interactive=True, visible=F0GPUVisible, ) gpu_info9 = gr.Textbox( label="GPU Info", value=gpu_info, visible=F0GPUVisible ) spk_id5 = gr.Slider( minimum=0, maximum=4, step=1, label="Speaker ID", value=0, interactive=True, visible=False ) but1.click( preprocess_dataset, [dataset_folder, training_name, sr2, np7], [info1], api_name="train_preprocess", ) with gr.Column(): f0method8 = gr.Radio( label="F0 extraction method", choices=["pm", "harvest", "dio", "rmvpe", "rmvpe_gpu"], value="rmvpe_gpu", interactive=True, ) gpus_rmvpe = gr.Textbox( label="GPU numbers to use separated by -, (e.g. 0-1-2)", value="%s-%s" % (gpus, gpus), interactive=True, visible=F0GPUVisible, ) but2 = gr.Button("2. Extract Features", variant="primary") info2 = gr.Textbox(label="Information", value="", max_lines=8) f0method8.change( fn=change_f0_method, inputs=[f0method8], outputs=[gpus_rmvpe], ) but2.click( extract_f0_feature, [ gpus6, np7, f0method8, if_f0_3, training_name, version19, gpus_rmvpe, ], [info2], api_name="train_extract_f0_feature", ) with gr.Column(): total_epoch11 = gr.Slider( minimum=2, maximum=1000, step=1, label="Epochs (more epochs may improve quality but takes longer)", value=150, interactive=True, ) but4 = gr.Button("3. Train Index", variant="primary") but3 = gr.Button("4. Train Model", variant="primary") info3 = gr.Textbox(label="Information", value="", max_lines=10) with gr.Accordion(label="General Settings", open=False): gpus16 = gr.Textbox( label="GPUs separated by -, (e.g. 0-1-2)", value="0", interactive=True, visible=True ) save_epoch10 = gr.Slider( minimum=1, maximum=50, step=1, label="Weight Saving Frequency", value=25, interactive=True, ) batch_size12 = gr.Slider( minimum=1, maximum=40, step=1, label="Batch Size", value=default_batch_size, interactive=True, ) if_save_latest13 = gr.Radio( label="Only save the latest model", choices=["yes", "no"], value="yes", interactive=True, visible=False ) if_cache_gpu17 = gr.Radio( label="If your dataset is UNDER 10 minutes, cache it to train faster", choices=["yes", "no"], value="no", interactive=True, ) if_save_every_weights18 = gr.Radio( label="Save small model at every save point", choices=["yes", "no"], value="yes", interactive=True, ) with gr.Accordion(label="Change pretrains", open=False): pretrained = lambda sr, letter: [os.path.abspath(os.path.join('assets/pretrained_v2', file)) for file in os.listdir('assets/pretrained_v2') if file.endswith('.pth') and sr in file and letter in file] pretrained_G14 = gr.Dropdown( label="pretrained G", # Get a list of all pretrained G model files in assets/pretrained_v2 that end with .pth choices = pretrained(sr2.value, 'G'), value=pretrained(sr2.value, 'G')[0] if len(pretrained(sr2.value, 'G')) > 0 else '', interactive=True, visible=True ) pretrained_D15 = gr.Dropdown( label="pretrained D", choices = pretrained(sr2.value, 'D'), value= pretrained(sr2.value, 'D')[0] if len(pretrained(sr2.value, 'G')) > 0 else '', visible=True, interactive=True ) with gr.Row(): download_model = gr.Button('5.Download Model') with gr.Row(): model_files = gr.Files(label='Your Model and Index file can be downloaded here:') download_model.click( fn=lambda name: os.listdir(f'assets/weights/{name}') + glob.glob(f'logs/{name.split(".")[0]}/added_*.index'), inputs=[training_name], outputs=[model_files, info3]) with gr.Row(): sr2.change( change_sr2, [sr2, if_f0_3, version19], [pretrained_G14, pretrained_D15], ) version19.change( change_version19, [sr2, if_f0_3, version19], [pretrained_G14, pretrained_D15, sr2], ) if_f0_3.change( change_f0, [if_f0_3, sr2, version19], [f0method8, pretrained_G14, pretrained_D15], ) with gr.Row(): but5 = gr.Button("1 Click Training", variant="primary", visible=False) but3.click( click_train, [ training_name, sr2, if_f0_3, spk_id5, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17, if_save_every_weights18, version19, ], info3, api_name="train_start", ) but4.click(train_index, [training_name, version19], info3) but5.click( train1key, [ training_name, sr2, if_f0_3, dataset_folder, spk_id5, np7, f0method8, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17, if_save_every_weights18, version19, gpus_rmvpe, ], info3, api_name="train_start_all", ) app.launch(share=True)