RVC/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-01-20 02:51:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Reformat and rewrite _get_name_params (#57)

Browse Source 
* Reformat

* rewrite _get_name_params

* Add workflow for automatic formatting

* Revert "Add workflow for automatic formatting"

This reverts commit 9111c5dbc1.

* revert Retrieval_based_Voice_Conversion_WebUI.ipynb

---------

Co-authored-by: 源文雨 <41315874+fumiama@users.noreply.github.com>
This commit is contained in:
Ftps
2023-04-15 20:44:24 +09:00
committed by GitHub
parent aaa893c4b1
commit c8261b2ccc
45 changed files with 4878 additions and 2456 deletions
Download Patch File Download Diff File Expand all files Collapse all files

116
extract_f0_print.py
View File

@@ -1,21 +1,26 @@
import os,traceback,sys,parselmouth
import os, traceback, sys, parselmouth
import librosa
import pyworld
from scipy.io import wavfile
import numpy as np,logging
logging.getLogger('numba').setLevel(logging.WARNING)
import numpy as np, logging
logging.getLogger("numba").setLevel(logging.WARNING)
from multiprocessing import Process
exp_dir = sys.argv[1]
f = open("%s/extract_f0_feature.log"%exp_dir, "a+")
f = open("%s/extract_f0_feature.log" % exp_dir, "a+")
def printt(strr):
print(strr)
f.write("%s\n" % strr)
f.flush()
n_p = int(sys.argv[2])
f0method = sys.argv[3]
class FeatureInput(object):
def __init__(self, samplerate=16000, hop_size=160):
self.fs = samplerate
@@ -27,21 +32,30 @@ class FeatureInput(object):
self.f0_mel_min = 1127 * np.log(1 + self.f0_min / 700)
self.f0_mel_max = 1127 * np.log(1 + self.f0_max / 700)
def compute_f0(self, path,f0_method):
def compute_f0(self, path, f0_method):
x, sr = librosa.load(path, self.fs)
p_len=x.shape[0]//self.hop
p_len = x.shape[0] // self.hop
assert sr == self.fs
if(f0_method=="pm"):
if f0_method == "pm":
time_step = 160 / 16000 * 1000
f0_min = 50
f0_max = 1100
f0 = parselmouth.Sound(x, sr).to_pitch_ac(
time_step=time_step / 1000, voicing_threshold=0.6,
pitch_floor=f0_min, pitch_ceiling=f0_max).selected_array['frequency']
pad_size=(p_len - len(f0) + 1) // 2
if(pad_size>0 or p_len - len(f0) - pad_size>0):
f0 = np.pad(f0,[[pad_size,p_len - len(f0) - pad_size]], mode='constant')
elif(f0_method=="harvest"):
f0 = (
parselmouth.Sound(x, sr)
.to_pitch_ac(
time_step=time_step / 1000,
voicing_threshold=0.6,
pitch_floor=f0_min,
pitch_ceiling=f0_max,
)
.selected_array["frequency"]
)
pad_size = (p_len - len(f0) + 1) // 2
if pad_size > 0 or p_len - len(f0) - pad_size > 0:
f0 = np.pad(
f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant"
)
elif f0_method == "harvest":
f0, t = pyworld.harvest(
x.astype(np.double),
fs=sr,
@@ -50,7 +64,7 @@ class FeatureInput(object):
frame_period=1000 * self.hop / sr,
)
f0 = pyworld.stonemask(x.astype(np.double), f0, t, self.fs)
elif(f0_method=="dio"):
elif f0_method == "dio":
f0, t = pyworld.dio(
x.astype(np.double),
fs=sr,
@@ -77,45 +91,67 @@ class FeatureInput(object):
)
return f0_coarse
def go(self,paths,f0_method):
if (len(paths) == 0): printt("no-f0-todo")
def go(self, paths, f0_method):
if len(paths) == 0:
printt("no-f0-todo")
else:
printt("todo-f0-%s"%len(paths))
n=max(len(paths)//5,1)#每个进程最多打印5条
for idx,(inp_path,opt_path1,opt_path2) in enumerate(paths):
printt("todo-f0-%s" % len(paths))
n = max(len(paths) // 5, 1) # 每个进程最多打印5条
for idx, (inp_path, opt_path1, opt_path2) in enumerate(paths):
try:
if(idx%n==0):printt("f0ing,now-%s,all-%s,-%s"%(idx,len(paths),inp_path))
if(os.path.exists(opt_path1+".npy")==True and os.path.exists(opt_path2+".npy")==True):continue
featur_pit = self.compute_f0(inp_path,f0_method)
np.save(opt_path2,featur_pit,allow_pickle=False,)#nsf
if idx % n == 0:
printt("f0ing,now-%s,all-%s,-%s" % (idx, len(paths), inp_path))
if (
os.path.exists(opt_path1 + ".npy") == True
and os.path.exists(opt_path2 + ".npy") == True
):
continue
featur_pit = self.compute_f0(inp_path, f0_method)
np.save(
opt_path2,
featur_pit,
allow_pickle=False,
) # nsf
coarse_pit = self.coarse_f0(featur_pit)
np.save(opt_path1,coarse_pit,allow_pickle=False,)#ori
np.save(
opt_path1,
coarse_pit,
allow_pickle=False,
) # ori
except:
printt("f0fail-%s-%s-%s" % (idx, inp_path,traceback.format_exc()))
printt("f0fail-%s-%s-%s" % (idx, inp_path, traceback.format_exc()))
if __name__=='__main__':
if __name__ == "__main__":
# exp_dir=r"E:\codes\py39\dataset\mi-test"
# n_p=16
# f = open("%s/log_extract_f0.log"%exp_dir, "w")
printt(sys.argv)
featureInput = FeatureInput()
paths=[]
inp_root= "%s/1_16k_wavs"%(exp_dir)
opt_root1="%s/2a_f0"%(exp_dir)
opt_root2="%s/2b-f0nsf"%(exp_dir)
paths = []
inp_root = "%s/1_16k_wavs" % (exp_dir)
opt_root1 = "%s/2a_f0" % (exp_dir)
opt_root2 = "%s/2b-f0nsf" % (exp_dir)
os.makedirs(opt_root1,exist_ok=True)
os.makedirs(opt_root2,exist_ok=True)
os.makedirs(opt_root1, exist_ok=True)
os.makedirs(opt_root2, exist_ok=True)
for name in sorted(list(os.listdir(inp_root))):
inp_path="%s/%s"%(inp_root,name)
if ("spec" in inp_path): continue
opt_path1="%s/%s"%(opt_root1,name)
opt_path2="%s/%s"%(opt_root2,name)
paths.append([inp_path,opt_path1,opt_path2])
inp_path = "%s/%s" % (inp_root, name)
if "spec" in inp_path:
continue
opt_path1 = "%s/%s" % (opt_root1, name)
opt_path2 = "%s/%s" % (opt_root2, name)
paths.append([inp_path, opt_path1, opt_path2])
ps=[]
ps = []
for i in range(n_p):
p=Process(target=featureInput.go,args=(paths[i::n_p],f0method,))
p = Process(
target=featureInput.go,
args=(
paths[i::n_p],
f0method,
),
)
p.start()
ps.append(p)
for p in ps: