Spaces:
Running
Running
File size: 35,946 Bytes
e71a85c 1291663 bdfa06b e71a85c bd8aed8 e71a85c 96e3ef5 2a362c7 580bab3 e71a85c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 |
import gradio as gr
import requests
import random
import os
import zipfile
import librosa
import time
from infer_rvc_python import BaseLoader
from pydub import AudioSegment
from tts_voice import tts_order_voice
import edge_tts
import tempfile
from audio_separator.separator import Separator
import model_handler
import psutil
import cpuinfo
from gradio.themes.base import Base
from gradio.themes.utils import colors, fonts, sizes
from typing import Iterable
language_dict = tts_order_voice
async def text_to_speech_edge(text, language_code):
voice = language_dict[language_code]
communicate = edge_tts.Communicate(text, voice)
with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
tmp_path = tmp_file.name
await communicate.save(tmp_path)
return tmp_path
try:
import spaces
spaces_status = True
except ImportError:
spaces_status = False
separator = Separator()
converter = BaseLoader(only_cpu=False, hubert_path=None, rmvpe_path=None)
global pth_file
global index_file
pth_file = "model.pth"
index_file = "model.index"
#CONFIGS
TEMP_DIR = "temp"
MODEL_PREFIX = "model"
PITCH_ALGO_OPT = [
"pm",
"harvest",
"crepe",
"rmvpe",
"rmvpe+",
]
UVR_5_MODELS = [
{"model_name": "BS-Roformer-Viperx-1297", "checkpoint": "model_bs_roformer_ep_317_sdr_12.9755.ckpt"},
{"model_name": "MDX23C-InstVoc HQ 2", "checkpoint": "MDX23C-8KFFT-InstVoc_HQ_2.ckpt"},
{"model_name": "Kim Vocal 2", "checkpoint": "Kim_Vocal_2.onnx"},
{"model_name": "5_HP-Karaoke", "checkpoint": "5_HP-Karaoke-UVR.pth"},
{"model_name": "UVR-DeNoise by FoxJoy", "checkpoint": "UVR-DeNoise.pth"},
{"model_name": "UVR-DeEcho-DeReverb by FoxJoy", "checkpoint": "UVR-DeEcho-DeReverb.pth"},
]
MODELS = [
{"model": "model.pth", "index": "model.index", "model_name": "Test Model"},
]
os.makedirs(TEMP_DIR, exist_ok=True)
def unzip_file(file):
filename = os.path.basename(file).split(".")[0]
with zipfile.ZipFile(file, 'r') as zip_ref:
zip_ref.extractall(os.path.join(TEMP_DIR, filename))
return True
def progress_bar(total, current):
return "[" + "=" * int(current / total * 20) + ">" + " " * (20 - int(current / total * 20)) + "] " + str(int(current / total * 100)) + "%"
def download_from_url(url, name=None):
if name is None:
raise ValueError("The model name must be provided")
if "/blob/" in url:
url = url.replace("/blob/", "/resolve/")
if "huggingface" not in url:
return ["The URL must be from huggingface", "Failed", "Failed"]
filename = os.path.join(TEMP_DIR, MODEL_PREFIX + str(random.randint(1, 1000)) + ".zip")
response = requests.get(url)
total = int(response.headers.get('content-length', 0))
if total > 500000000:
return ["The file is too large. You can only download files up to 500 MB in size.", "Failed", "Failed"]
current = 0
with open(filename, "wb") as f:
for data in response.iter_content(chunk_size=4096):
f.write(data)
current += len(data)
print(progress_bar(total, current), end="\r") #
try:
unzip_file(filename)
except Exception as e:
return ["Failed to unzip the file", "Failed", "Failed"]
unzipped_dir = os.path.join(TEMP_DIR, os.path.basename(filename).split(".")[0])
pth_files = []
index_files = []
for root, dirs, files in os.walk(unzipped_dir):
for file in files:
if file.endswith(".pth"):
pth_files.append(os.path.join(root, file))
elif file.endswith(".index"):
index_files.append(os.path.join(root, file))
print(pth_files, index_files)
global pth_file
global index_file
pth_file = pth_files[0]
index_file = index_files[0]
print(pth_file)
print(index_file)
if name == "":
name = pth_file.split(".")[0]
MODELS.append({"model": pth_file, "index": index_file, "model_name": name})
return ["Downloaded as " + name, pth_files[0], index_files[0]]
def inference(audio, model_name):
output_data = inf_handler(audio, model_name)
vocals = output_data[0]
inst = output_data[1]
return vocals, inst
if spaces_status:
@spaces.GPU()
def convert_now(audio_files, random_tag, converter):
return converter(
audio_files,
random_tag,
overwrite=False,
parallel_workers=8
)
else:
def convert_now(audio_files, random_tag, converter):
return converter(
audio_files,
random_tag,
overwrite=False,
parallel_workers=8
)
def calculate_remaining_time(epochs, seconds_per_epoch):
total_seconds = epochs * seconds_per_epoch
hours = total_seconds // 3600
minutes = (total_seconds % 3600) // 60
seconds = total_seconds % 60
if hours == 0:
return f"{int(minutes)} minutes"
elif hours == 1:
return f"{int(hours)} hour and {int(minutes)} minutes"
else:
return f"{int(hours)} hours and {int(minutes)} minutes"
def inf_handler(audio, model_name):
model_found = False
for model_info in UVR_5_MODELS:
if model_info["model_name"] == model_name:
separator.load_model(model_info["checkpoint"])
model_found = True
break
if not model_found:
separator.load_model()
output_files = separator.separate(audio)
vocals = output_files[0]
inst = output_files[1]
return vocals, inst
def run(
model,
audio_files,
pitch_alg,
pitch_lvl,
index_inf,
r_m_f,
e_r,
c_b_p,
):
if not audio_files:
raise ValueError("The audio pls")
if isinstance(audio_files, str):
audio_files = [audio_files]
try:
duration_base = librosa.get_duration(filename=audio_files[0])
print("Duration:", duration_base)
except Exception as e:
print(e)
random_tag = "USER_"+str(random.randint(10000000, 99999999))
file_m = model
print("File model:", file_m)
# get from MODELS
for model in MODELS:
if model["model_name"] == file_m:
print(model)
file_m = model["model"]
file_index = model["index"]
break
if not file_m.endswith(".pth"):
raise ValueError("The model file must be a .pth file")
print("Random tag:", random_tag)
print("File model:", file_m)
print("Pitch algorithm:", pitch_alg)
print("Pitch level:", pitch_lvl)
print("File index:", file_index)
print("Index influence:", index_inf)
print("Respiration median filtering:", r_m_f)
print("Envelope ratio:", e_r)
converter.apply_conf(
tag=random_tag,
file_model=file_m,
pitch_algo=pitch_alg,
pitch_lvl=pitch_lvl,
file_index=file_index,
index_influence=index_inf,
respiration_median_filtering=r_m_f,
envelope_ratio=e_r,
consonant_breath_protection=c_b_p,
resample_sr=44100 if audio_files[0].endswith('.mp3') else 0,
)
time.sleep(0.1)
result = convert_now(audio_files, random_tag, converter)
print("Result:", result)
return result[0]
def upload_model(index_file, pth_file, model_name):
pth_file = pth_file.name
index_file = index_file.name
MODELS.append({"model": pth_file, "index": index_file, "model_name": model_name})
return "Uploaded!"
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",
)
applio = Applio()
with gr.Blocks(theme=applio, title="Ilaria RVC 💖") as demo:
gr.Markdown("## Ilaria RVC 💖")
with gr.Tab("Inference"):
sound_gui = gr.Audio(value=None,type="filepath",autoplay=False,visible=True,)
def update():
print(MODELS)
return gr.Dropdown(label="Model",choices=[model["model_name"] for model in MODELS],visible=True,interactive=True, value=MODELS[0]["model_name"],)
with gr.Row():
models_dropdown = gr.Dropdown(label="Model",choices=[model["model_name"] for model in MODELS],visible=True,interactive=True, value=MODELS[0]["model_name"],)
refresh_button = gr.Button("Refresh Models")
refresh_button.click(update, outputs=[models_dropdown])
with gr.Accordion("Ilaria TTS", open=False):
text_tts = gr.Textbox(label="Text", placeholder="Hello!", lines=3, interactive=True,)
dropdown_tts = gr.Dropdown(label="Language and Model",choices=list(language_dict.keys()),interactive=True, value=list(language_dict.keys())[0])
button_tts = gr.Button("Speak", variant="primary",)
button_tts.click(text_to_speech_edge, inputs=[text_tts, dropdown_tts], outputs=[sound_gui])
with gr.Accordion("Settings", open=False):
pitch_algo_conf = gr.Dropdown(PITCH_ALGO_OPT,value=PITCH_ALGO_OPT[4],label="Pitch algorithm",visible=True,interactive=True,)
pitch_lvl_conf = gr.Slider(label="Pitch level (lower -> 'male' while higher -> 'female')",minimum=-24,maximum=24,step=1,value=0,visible=True,interactive=True,)
index_inf_conf = gr.Slider(minimum=0,maximum=1,label="Index influence -> How much accent is applied",value=0.75,)
respiration_filter_conf = gr.Slider(minimum=0,maximum=7,label="Respiration median filtering",value=3,step=1,interactive=True,)
envelope_ratio_conf = gr.Slider(minimum=0,maximum=1,label="Envelope ratio",value=0.25,interactive=True,)
consonant_protec_conf = gr.Slider(minimum=0,maximum=0.5,label="Consonant breath protection",value=0.5,interactive=True,)
button_conf = gr.Button("Convert",variant="primary",)
output_conf = gr.Audio(type="filepath",label="Output",)
button_conf.click(lambda :None, None, output_conf)
button_conf.click(
run,
inputs=[
models_dropdown,
sound_gui,
pitch_algo_conf,
pitch_lvl_conf,
index_inf_conf,
respiration_filter_conf,
envelope_ratio_conf,
consonant_protec_conf,
],
outputs=[output_conf],
)
with gr.Tab("Model Loader (Download and Upload)"):
with gr.Accordion("Model Downloader", open=False):
gr.Markdown(
"Download the model from the following URL and upload it here. (Huggingface RVC model)"
)
model = gr.Textbox(lines=1, label="Model URL")
name = gr.Textbox(lines=1, label="Model Name", placeholder="Model Name")
download_button = gr.Button("Download Model")
status = gr.Textbox(lines=1, label="Status", placeholder="Waiting....", interactive=False)
model_pth = gr.Textbox(lines=1, label="Model pth file", placeholder="Waiting....", interactive=False)
index_pth = gr.Textbox(lines=1, label="Index pth file", placeholder="Waiting....", interactive=False)
download_button.click(download_from_url, [model, name], outputs=[status, model_pth, index_pth])
with gr.Accordion("Upload A Model", open=False):
index_file_upload = gr.File(label="Index File (.index)")
pth_file_upload = gr.File(label="Model File (.pth)")
model_name = gr.Textbox(label="Model Name", placeholder="Model Name")
upload_button = gr.Button("Upload Model")
upload_status = gr.Textbox(lines=1, label="Status", placeholder="Waiting....", interactive=False)
upload_button.click(upload_model, [index_file_upload, pth_file_upload, model_name], upload_status)
with gr.Tab("Vocal Separator (UVR)"):
gr.Markdown("Separate vocals and instruments from an audio file using UVR models. - This is only on CPU due to ZeroGPU being ZeroGPU :(")
uvr5_audio_file = gr.Audio(label="Audio File",type="filepath")
with gr.Row():
uvr5_model = gr.Dropdown(label="Model", choices=[model["model_name"] for model in UVR_5_MODELS])
uvr5_button = gr.Button("Separate Vocals", variant="primary",)
uvr5_output_voc = gr.Audio(type="filepath", label="Output 1",)
uvr5_output_inst = gr.Audio(type="filepath", label="Output 2",)
uvr5_button.click(inference, [uvr5_audio_file, uvr5_model], [uvr5_output_voc, uvr5_output_inst])
with gr.Tab("Extra"):
with gr.Accordion("Model Information", open=False):
def json_to_markdown_table(json_data):
table = "| Key | Value |\n| --- | --- |\n"
for key, value in json_data.items():
table += f"| {key} | {value} |\n"
return table
def model_info(name):
for model in MODELS:
if model["model_name"] == name:
print(model["model"])
info = model_handler.model_info(model["model"])
info2 = {
"Model Name": model["model_name"],
"Model Config": info['config'],
"Epochs Trained": info['epochs'],
"Sample Rate": info['sr'],
"Pitch Guidance": info['f0'],
"Model Precision": info['size'],
}
return gr.Markdown(json_to_markdown_table(info2))
return "Model not found"
def update():
print(MODELS)
return gr.Dropdown(label="Model", choices=[model["model_name"] for model in MODELS])
with gr.Row():
model_info_dropdown = gr.Dropdown(label="Model", choices=[model["model_name"] for model in MODELS])
refresh_button = gr.Button("Refresh Models")
refresh_button.click(update, outputs=[model_info_dropdown])
model_info_button = gr.Button("Get Model Information")
model_info_output = gr.Textbox(value="Waiting...",label="Output", interactive=False)
model_info_button.click(model_info, [model_info_dropdown], [model_info_output])
with gr.Accordion("Training Time Calculator", open=False):
with gr.Column():
epochs_input = gr.Number(label="Number of Epochs")
seconds_input = gr.Number(label="Seconds per Epoch")
calculate_button = gr.Button("Calculate Time Remaining")
remaining_time_output = gr.Textbox(label="Remaining Time", interactive=False)
calculate_button.click(calculate_remaining_time,inputs=[epochs_input, seconds_input],outputs=[remaining_time_output])
with gr.Accordion("Model Fusion", open=False):
with gr.Group():
def merge(ckpt_a, ckpt_b, alpha_a, sr_, if_f0_, info__, name_to_save0, version_2):
for model in MODELS:
if model["model_name"] == ckpt_a:
ckpt_a = model["model"]
if model["model_name"] == ckpt_b:
ckpt_b = model["model"]
path = model_handler.merge(ckpt_a, ckpt_b, alpha_a, sr_, if_f0_, info__, name_to_save0, version_2)
if path == "Fail to merge the models. The model architectures are not the same.":
return "Fail to merge the models. The model architectures are not the same."
else:
MODELS.append({"model": path, "index": None, "model_name": name_to_save0})
return "Merged, saved as " + name_to_save0
gr.Markdown(value="Strongly suggested to use only very clean models.")
with gr.Row():
def update():
print(MODELS)
return gr.Dropdown(label="Model A", choices=[model["model_name"] for model in MODELS]), gr.Dropdown(label="Model B", choices=[model["model_name"] for model in MODELS])
refresh_button_fusion = gr.Button("Refresh Models")
ckpt_a = gr.Dropdown(label="Model A", choices=[model["model_name"] for model in MODELS])
ckpt_b = gr.Dropdown(label="Model B", choices=[model["model_name"] for model in MODELS])
refresh_button_fusion.click(update, outputs=[ckpt_a, ckpt_b])
alpha_a = gr.Slider(
minimum=0,
maximum=1,
label="Weight of the first model over the second",
value=0.5,
interactive=True,
)
with gr.Group():
with gr.Row():
sr_ = gr.Radio(
label="Sample rate of both models",
choices=["32k","40k", "48k"],
value="32k",
interactive=True,
)
if_f0_ = gr.Radio(
label="Pitch Guidance",
choices=["Yes", "Nah"],
value="Yes",
interactive=True,
)
info__ = gr.Textbox(
label="Add informations to the model",
value="",
max_lines=8,
interactive=True,
visible=False
)
name_to_save0 = gr.Textbox(
label="Final Model name",
value="",
max_lines=1,
interactive=True,
)
version_2 = gr.Radio(
label="Versions of the models",
choices=["v1", "v2"],
value="v2",
interactive=True,
)
with gr.Group():
with gr.Row():
but6 = gr.Button("Fuse the two models", variant="primary")
info4 = gr.Textbox(label="Output", value="", max_lines=8)
but6.click(
merge,
[ckpt_a,ckpt_b,alpha_a,sr_,if_f0_,info__,name_to_save0,version_2,],info4,api_name="ckpt_merge",)
with gr.Accordion("Model Quantization", open=False):
gr.Markdown("Quantize the model to a lower precision. - soon™ or never™ 😎")
with gr.Accordion("Debug", open=False):
def json_to_markdown_table(json_data):
table = "| Key | Value |\n| --- | --- |\n"
for key, value in json_data.items():
table += f"| {key} | {value} |\n"
return table
gr.Markdown("View the models that are currently loaded in the instance.")
gr.Markdown(json_to_markdown_table({"Models": len(MODELS), "UVR Models": len(UVR_5_MODELS)}))
gr.Markdown("View the current status of the instance.")
status = {
"Status": "Running", # duh lol
"Models": len(MODELS),
"UVR Models": len(UVR_5_MODELS),
"CPU Usage": f"{psutil.cpu_percent()}%",
"RAM Usage": f"{psutil.virtual_memory().percent}%",
"CPU": f"{cpuinfo.get_cpu_info()['brand_raw']}",
"System Uptime": f"{round(time.time() - psutil.boot_time(), 2)} seconds",
"System Load Average": f"{psutil.getloadavg()}",
"====================": "====================",
"CPU Cores": psutil.cpu_count(),
"CPU Threads": psutil.cpu_count(logical=True),
"RAM Total": f"{round(psutil.virtual_memory().total / 1024**3, 2)} GB",
"RAM Used": f"{round(psutil.virtual_memory().used / 1024**3, 2)} GB",
"CPU Frequency": f"{psutil.cpu_freq().current} MHz",
"====================": "====================",
"GPU": "A100 - Do a request (Inference, you won't see it either way)",
}
gr.Markdown(json_to_markdown_table(status))
with gr.Tab("Credits"):
gr.Markdown(
"""
Ilaria RVC made by [Ilaria](https://huggingface.co/TheStinger) suport her on [ko-fi](https://ko-fi.com/ilariaowo)
The Inference code is made by [r3gm](https://huggingface.co/r3gm) (his module helped form this space 💖)
made with ❤️ by [mikus](https://github.com/cappuch) - made the ui!
## In loving memory of JLabDX 🕊️
"""
)
with gr.Tab(("")):
gr.Markdown('''
''')
demo.queue(api_open=False).launch(show_api=False)
|