1
0
mirror of synced 2024-11-13 18:30:51 +01:00

Add files via upload

This commit is contained in:
RVC-Boss 2023-04-27 23:34:03 +08:00 committed by GitHub
parent a149107c5a
commit af208d5210
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 352 additions and 326 deletions

View File

@ -1,2 +1,2 @@
runtime\python.exe infer-web.py --pycmd runtime\python.exe
runtime\python.exe infer-web.py --pycmd runtime\python.exe --port 7897
pause

View File

@ -1,5 +1,5 @@
from multiprocessing import cpu_count
import threading
import threading,pdb,librosa
from time import sleep
from subprocess import Popen
from time import sleep
@ -17,6 +17,7 @@ os.environ["TEMP"] = tmp
warnings.filterwarnings("ignore")
torch.manual_seed(114514)
from i18n import I18nAuto
import ffmpeg
i18n = I18nAuto()
# 判断是否有能用来训练和加速推理的N卡
@ -235,7 +236,7 @@ def vc_multi(
yield traceback.format_exc()
def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins):
def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins,agg):
infos = []
try:
inp_root = inp_root.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
@ -246,6 +247,7 @@ def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins):
save_root_ins.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
)
pre_fun = _audio_pre_(
agg=int(agg),
model_path=os.path.join(weight_uvr5_root, model_name + ".pth"),
device=device,
is_half=is_half,
@ -254,10 +256,25 @@ def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins):
paths = [os.path.join(inp_root, name) for name in os.listdir(inp_root)]
else:
paths = [path.name for path in paths]
for name in paths:
inp_path = os.path.join(inp_root, name)
for path in paths:
inp_path = os.path.join(inp_root, path)
need_reformat=1
done=0
try:
info = ffmpeg.probe(inp_path, cmd="ffprobe")
if(info["streams"][0]["channels"]==2 and info["streams"][0]["sample_rate"]=="44100"):
need_reformat=0
pre_fun._path_audio_(inp_path, save_root_ins, save_root_vocal)
done=1
except:
need_reformat = 1
traceback.print_exc()
if(need_reformat==1):
tmp_path="%s/%s.reformatted.wav"%(tmp,os.path.basename(inp_path))
os.system("ffmpeg -i %s -vn -acodec pcm_s16le -ac 2 -ar 44100 %s -y"%(inp_path,tmp_path))
inp_path=tmp_path
try:
if(done==0):pre_fun._path_audio_(inp_path, save_root_ins, save_root_vocal)
infos.append("%s->Success" % (os.path.basename(inp_path)))
yield "\n".join(infos)
except:
@ -1147,6 +1164,15 @@ with gr.Blocks() as app:
)
with gr.Column():
model_choose = gr.Dropdown(label=i18n("模型"), choices=uvr5_names)
agg = gr.Slider(
minimum=0,
maximum=20,
step=1,
label="人声提取激进程度",
value=10,
interactive=True,
visible=False#先不开放调整
)
opt_vocal_root = gr.Textbox(
label=i18n("指定输出人声文件夹"), value="opt"
)
@ -1161,6 +1187,7 @@ with gr.Blocks() as app:
opt_vocal_root,
wav_inputs,
opt_ins_root,
agg
],
[vc_output4],
)
@ -1246,7 +1273,7 @@ with gr.Blocks() as app:
with gr.Row():
save_epoch10 = gr.Slider(
minimum=0,
maximum=200,
maximum=50,
step=1,
label=i18n("保存频率save_every_epoch"),
value=5,

View File

@ -13,7 +13,7 @@ from scipy.io import wavfile
class _audio_pre_:
def __init__(self, model_path, device, is_half):
def __init__(self, agg,model_path, device, is_half):
self.model_path = model_path
self.device = device
self.data = {
@ -22,7 +22,7 @@ class _audio_pre_:
"tta": False,
# Constants
"window_size": 512,
"agg": 10,
"agg": agg,
"high_end_process": "mirroring",
}
nn_arch_sizes = [
@ -139,7 +139,7 @@ class _audio_pre_:
wav_instrument = spec_utils.cmb_spectrogram_to_wave(y_spec_m, self.mp)
print("%s instruments done" % name)
wavfile.write(
os.path.join(ins_root, "instrument_{}.wav".format(name)),
os.path.join(ins_root, "instrument_{}_{}.wav".format(name,self.data["agg"])),
self.mp.param["sr"],
(np.array(wav_instrument) * 32768).astype("int16"),
) #
@ -155,7 +155,7 @@ class _audio_pre_:
wav_vocals = spec_utils.cmb_spectrogram_to_wave(v_spec_m, self.mp)
print("%s vocals done" % name)
wavfile.write(
os.path.join(vocal_root, "vocal_{}.wav".format(name)),
os.path.join(vocal_root, "vocal_{}_{}.wav".format(name,self.data["agg"])),
self.mp.param["sr"],
(np.array(wav_vocals) * 32768).astype("int16"),
)

View File

@ -45,7 +45,7 @@ global_step = 0
def main():
# n_gpus = torch.cuda.device_count()
os.environ["MASTER_ADDR"] = "localhost"
os.environ["MASTER_PORT"] = "51515"
os.environ["MASTER_PORT"] = "51545"
mp.spawn(
run,

View File

@ -123,7 +123,6 @@ class VC(object):
# _, I = index.search(npy, 1)
# npy = big_npy[I.squeeze()]
#by github @nadare881
score, ix = index.search(npy, k=8)
weight = np.square(1 / score)
weight /= weight.sum(axis=1, keepdims=True)