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

rewrite oneclick_train

Browse Source
This commit is contained in:
Ftps
2023-08-28 23:56:39 +09:00
parent 740625fd2b
commit 6e14c7b5f5
11 changed files with 21 additions and 270 deletions
Download Patch File Download Diff File Expand all files Collapse all files

281
infer-web.py
View File

@@ -705,280 +705,21 @@ def train1key(
infos.append(strr)
return "\n".join(infos)
model_log_dir = "%s/logs/%s" % (now_dir, exp_dir1)
preprocess_log_path = "%s/preprocess.log" % model_log_dir
extract_f0_feature_log_path = "%s/extract_f0_feature.log" % model_log_dir
gt_wavs_dir = "%s/0_gt_wavs" % model_log_dir
feature_dir = (
"%s/3_feature256" % model_log_dir
if version19 == "v1"
else "%s/3_feature768" % model_log_dir
)
os.makedirs(model_log_dir, exist_ok=True)
#########step1:处理数据
open(preprocess_log_path, "w").close()
cmd = (
get_quoted_python_cmd()
+ ' trainset_preprocess_pipeline_print.py "%s" %s %s "%s" '
% (trainset_dir4, sr_dict[sr2], np7, model_log_dir)
+ str(config.noparallel)
)
####### step1:处理数据
yield get_info_str(i18n("step1:正在处理数据"))
yield get_info_str(cmd)
p = Popen(cmd, shell=True)
p.wait()
with open(preprocess_log_path, "r") as f:
print(f.read())
#########step2a:提取音高
open(extract_f0_feature_log_path, "w")
if if_f0_3:
yield get_info_str("step2a:正在提取音高")
if f0method8 != "rmvpe_gpu":
cmd = config.python_cmd + ' extract_f0_print.py "%s" %s %s' % (
model_log_dir,
np7,
f0method8,
)
yield get_info_str(cmd)
p = Popen(cmd, shell=True, cwd=now_dir)
p.wait()
else:
if gpus_rmvpe != "-":
gpus_rmvpe = gpus_rmvpe.split("-")
leng = len(gpus_rmvpe)
ps = []
for idx, n_g in enumerate(gpus_rmvpe):
cmd = (
get_quoted_python_cmd()
+ ' extract_f0_rmvpe.py %s %s %s "%s" %s '
% (
leng,
idx,
n_g,
model_log_dir,
config.is_half,
)
)
yield get_info_str(cmd)
p = Popen(
cmd, shell=True, cwd=now_dir
) # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
ps.append(p)
for p in ps:
p.wait()
else: # dml
cmd = config.python_cmd + ' extract_f0_rmvpe_dml.py "%s" ' % (
model_log_dir
)
yield get_info_str(cmd)
p = Popen(
cmd, shell=True, cwd=now_dir
) # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
p.wait()
with open(extract_f0_feature_log_path, "r") as f:
print(f.read())
else:
yield get_info_str(i18n("step2a:无需提取音高"))
#######step2b:提取特征
yield get_info_str(i18n("step2b:正在提取特征"))
gpus = gpus16.split("-")
leng = len(gpus)
ps = []
for idx, n_g in enumerate(gpus):
cmd = (
get_quoted_python_cmd()
+ ' extract_feature_print.py %s %s %s %s "%s" %s'
% (
config.device,
leng,
idx,
n_g,
model_log_dir,
version19,
)
)
yield get_info_str(cmd)
p = Popen(
cmd, shell=True, cwd=now_dir
) # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
ps.append(p)
for p in ps:
p.wait()
with open(extract_f0_feature_log_path, "r") as f:
print(f.read())
#######step3a:训练模型
[get_info_str(_) for _ in preprocess_dataset(trainset_dir4, exp_dir1, sr2, np7)]
####### step2a:提取音高
yield get_info_str(i18n("step2:正在提取音高&正在提取特征"))
[get_info_str(_) for _ in extract_f0_feature(gpus16, np7, f0method8, if_f0_3, exp_dir1, version19, gpus_rmvpe)]
####### step3a:训练模型
yield get_info_str(i18n("step3a:正在训练模型"))
# 生成filelist
if if_f0_3:
f0_dir = "%s/2a_f0" % model_log_dir
f0nsf_dir = "%s/2b-f0nsf" % model_log_dir
names = (
set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)])
& set([name.split(".")[0] for name in os.listdir(feature_dir)])
& set([name.split(".")[0] for name in os.listdir(f0_dir)])
& set([name.split(".")[0] for name in os.listdir(f0nsf_dir)])
)
else:
names = set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)]) & set(
[name.split(".")[0] for name in os.listdir(feature_dir)]
)
opt = []
for name in names:
if if_f0_3:
opt.append(
"%s/%s.wav|%s/%s.npy|%s/%s.wav.npy|%s/%s.wav.npy|%s"
% (
gt_wavs_dir.replace("\\", "\\\\"),
name,
feature_dir.replace("\\", "\\\\"),
name,
f0_dir.replace("\\", "\\\\"),
name,
f0nsf_dir.replace("\\", "\\\\"),
name,
spk_id5,
)
)
else:
opt.append(
"%s/%s.wav|%s/%s.npy|%s"
% (
gt_wavs_dir.replace("\\", "\\\\"),
name,
feature_dir.replace("\\", "\\\\"),
name,
spk_id5,
)
)
fea_dim = 256 if version19 == "v1" else 768
if if_f0_3:
for _ in range(2):
opt.append(
"%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s/logs/mute/2a_f0/mute.wav.npy|%s/logs/mute/2b-f0nsf/mute.wav.npy|%s"
% (now_dir, sr2, now_dir, fea_dim, now_dir, now_dir, spk_id5)
)
else:
for _ in range(2):
opt.append(
"%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s"
% (now_dir, sr2, now_dir, fea_dim, spk_id5)
)
shuffle(opt)
with open("%s/filelist.txt" % model_log_dir, "w") as f:
f.write("\n".join(opt))
yield get_info_str("write filelist done")
if gpus16:
cmd = get_quoted_python_cmd() + ' train_nsf_sim_cache_sid_load_pretrain.py -e "%s" -sr %s -f0 %s -bs %s -g %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s' % (
exp_dir1,
sr2,
1 if if_f0_3 else 0,
batch_size12,
gpus16,
total_epoch11,
save_epoch10,
"-pg %s" % pretrained_G14 if pretrained_G14 != "" else "",
"-pd %s" % pretrained_D15 if pretrained_D15 != "" else "",
1 if if_save_latest13 == i18n("是") else 0,
1 if if_cache_gpu17 == i18n("是") else 0,
1 if if_save_every_weights18 == i18n("是") else 0,
version19,
)
else:
cmd = (
config.python_cmd
+ ' train_nsf_sim_cache_sid_load_pretrain.py -e "%s" -sr %s -f0 %s -bs %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s'
% (
exp_dir1,
sr2,
1 if if_f0_3 else 0,
batch_size12,
total_epoch11,
save_epoch10,
"-pg %s" % pretrained_G14 if pretrained_G14 != "" else "",
"-pd %s" % pretrained_D15 if pretrained_D15 != "" else "",
1 if if_save_latest13 == i18n("是") else 0,
1 if if_cache_gpu17 == i18n("是") else 0,
1 if if_save_every_weights18 == i18n("是") else 0,
version19,
)
)
yield get_info_str(cmd)
p = Popen(cmd, shell=True, cwd=now_dir)
p.wait()
click_train(exp_dir1, 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)
yield get_info_str(i18n("训练结束, 您可查看控制台训练日志或实验文件夹下的train.log"))
#######step3b:训练索引
npys = []
listdir_res = list(os.listdir(feature_dir))
for name in sorted(listdir_res):
phone = np.load("%s/%s" % (feature_dir, name))
npys.append(phone)
big_npy = np.concatenate(npys, 0)
big_npy_idx = np.arange(big_npy.shape[0])
np.random.shuffle(big_npy_idx)
big_npy = big_npy[big_npy_idx]
if big_npy.shape[0] > 2e5:
# if(1):
info = "Trying doing kmeans %s shape to 10k centers." % big_npy.shape[0]
print(info)
yield get_info_str(info)
try:
big_npy = (
MiniBatchKMeans(
n_clusters=10000,
verbose=True,
batch_size=256 * config.n_cpu,
compute_labels=False,
init="random",
)
.fit(big_npy)
.cluster_centers_
)
except:
info = traceback.format_exc()
print(info)
yield get_info_str(info)
np.save("%s/total_fea.npy" % model_log_dir, big_npy)
n_ivf = min(int(16 * np.sqrt(big_npy.shape[0])), big_npy.shape[0] // 39)
yield get_info_str("%s,%s" % (big_npy.shape, n_ivf))
index = faiss.index_factory(256 if version19 == "v1" else 768, "IVF%s,Flat" % n_ivf)
yield get_info_str("training index")
index_ivf = faiss.extract_index_ivf(index) #
index_ivf.nprobe = 1
index.train(big_npy)
faiss.write_index(
index,
"%s/trained_IVF%s_Flat_nprobe_%s_%s_%s.index"
% (
model_log_dir.replace(now_dir + "/", ""),
n_ivf,
index_ivf.nprobe,
exp_dir1,
version19,
),
)
yield get_info_str("adding index")
batch_size_add = 8192
for i in range(0, big_npy.shape[0], batch_size_add):
index.add(big_npy[i : i + batch_size_add])
faiss.write_index(
index,
"%s/added_IVF%s_Flat_nprobe_%s_%s_%s.index"
% (
model_log_dir.replace(now_dir + "/", ""),
n_ivf,
index_ivf.nprobe,
exp_dir1,
version19,
),
)
yield get_info_str(
"成功构建索引, added_IVF%s_Flat_nprobe_%s_%s_%s.index"
% (n_ivf, index_ivf.nprobe, exp_dir1, version19)
)
####### step3b:训练索引
[get_info_str(_) for _ in train_index(exp_dir1, version19)]
yield get_info_str(i18n("全流程结束！"))