Cool_Tools/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of synced 2025-02-25 14:34:38 +01:00
Code Releases Wiki Activity

Format code (#526)

Browse Source 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
This commit is contained in:
github-actions[bot] 2023-06-18 10:39:56 +00:00 committed by GitHub
parent f92a923487
commit a7647e4094
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 91 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
extract_feature_print.py
View File

@ -64,8 +64,11 @@ def readwave(wav_path, normalize=False):
# HuBERT model
printt("load model(s) from {}".format(model_path))
# if hubert model is exist
if (os.access(model_path, os.F_OK) == False):
printt("Error: Extracting is shut down because %s does not exist, you may download it from https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main" % model_path)
if os.access(model_path, os.F_OK) == False:
printt(
"Error: Extracting is shut down because %s does not exist, you may download it from https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main"
% model_path
)
exit(0)
models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task(
[model_path],

20
gui.py
View File

@ -469,21 +469,21 @@ class GUI:
self.flag_vc = False
def set_values(self, values):
if(len(values["pth_path"].strip()) == 0):
sg.popup(i18n('请选择pth文件'))
if len(values["pth_path"].strip()) == 0:
sg.popup(i18n("请选择pth文件"))
return False
if(len(values["index_path"].strip()) == 0):
sg.popup(i18n('请选择index文件'))
if len(values["index_path"].strip()) == 0:
sg.popup(i18n("请选择index文件"))
return False
pattern = re.compile("[^\x00-\x7F]+")
if(pattern.findall(values["hubert_path"])):
sg.popup(i18n('hubert模型路径不可包含中文'))
if pattern.findall(values["hubert_path"]):
sg.popup(i18n("hubert模型路径不可包含中文"))
return False
if(pattern.findall(values["pth_path"])):
sg.popup(i18n('pth文件路径不可包含中文'))
if pattern.findall(values["pth_path"]):
sg.popup(i18n("pth文件路径不可包含中文"))
return False
if(pattern.findall(values["index_path"])):
sg.popup(i18n('index文件路径不可包含中文'))
if pattern.findall(values["index_path"]):
sg.popup(i18n("index文件路径不可包含中文"))
return False
self.set_devices(values["sg_input_device"], values["sg_output_device"])
self.config.hubert_path = os.path.join(current_dir, "hubert_base.pt")

67
infer-web.py
View File

@ -1,6 +1,7 @@
import os
import shutil
import sys
now_dir = os.getcwd()
sys.path.append(now_dir)
import traceback, pdb
@ -434,11 +435,23 @@ def get_vc(sid,to_return_protect0,to_return_protect1):
tgt_sr = cpt["config"][-1]
cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0] # n_spk
if_f0 = cpt.get("f0", 1)
if(if_f0==0):
to_return_protect0=to_return_protect1={"visible": False, "value": 0.5, "__type__": "update"}
if if_f0 == 0:
to_return_protect0 = to_return_protect1 = {
"visible": False,
"value": 0.5,
"__type__": "update",
}
else:
to_return_protect0 ={"visible": True, "value": to_return_protect0, "__type__": "update"}
to_return_protect1 ={"visible": True, "value": to_return_protect1, "__type__": "update"}
to_return_protect0 = {
"visible": True,
"value": to_return_protect0,
"__type__": "update",
}
to_return_protect1 = {
"visible": True,
"value": to_return_protect1,
"__type__": "update",
}
version = cpt.get("version", "v1")
if version == "v1":
if if_f0 == 1:
@ -459,7 +472,11 @@ def get_vc(sid,to_return_protect0,to_return_protect1):
net_g = net_g.float()
vc = VC(tgt_sr, config)
n_spk = cpt["config"][-3]
return {"visible": True, "maximum": n_spk, "__type__": "update"},to_return_protect0,to_return_protect1
return (
{"visible": True, "maximum": n_spk, "__type__": "update"},
to_return_protect0,
to_return_protect1,
)
def change_choices():
@ -665,8 +682,13 @@ def change_sr2(sr2, if_f0_3, version19):
def change_version19(sr2, if_f0_3, version19):
path_str = "" if version19 == "v1" else "_v2"
if(sr2=="32k"and version19=="v1"):sr2="40k"
to_return_sr2= {"choices": ["40k","48k"], "__type__": "update"} if version19=="v1"else {"choices": ["32k","40k","48k"], "__type__": "update"}
if sr2 == "32k" and version19 == "v1":
sr2 = "40k"
to_return_sr2 = (
{"choices": ["40k", "48k"], "__type__": "update"}
if version19 == "v1"
else {"choices": ["32k", "40k", "48k"], "__type__": "update"}
)
f0_str = "f0" if if_f0_3 else ""
if_pretrained_generator_exist = os.access(
"pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2), os.F_OK
@ -691,7 +713,7 @@ def change_version19(sr2, if_f0_3, version19):
"pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2)
if if_pretrained_discriminator_exist
else "",
to_return_sr2
to_return_sr2,
)
@ -893,12 +915,22 @@ def train_index(exp_dir1, version19):
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 big_npy.shape[0] > 2e5:
# if(1):
infos.append("Trying doing kmeans %s shape to 10k centers." % big_npy.shape[0])
yield "\n".join(infos)
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_
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)
@ -1147,13 +1179,23 @@ def train1key(
np.random.shuffle(big_npy_idx)
big_npy = big_npy[big_npy_idx]
if(big_npy.shape[0]>2e5):
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_
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)
@ -1207,7 +1249,6 @@ def change_info_(ckpt_path):
return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"}
def export_onnx(ModelPath, ExportedPath):
cpt = torch.load(ModelPath, map_location="cpu")
cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]

1
infer_pack/onnx_inference.py
View File

@ -3,6 +3,7 @@ import librosa
import numpy as np
import soundfile
class ContentVec:
def __init__(self, vec_path="pretrained/vec-768-layer-12.onnx", device=None):
print("load model(s) from {}".format(vec_path))

2
train_nsf_sim_cache_sid_load_pretrain.py
View File

@ -192,7 +192,6 @@ def run(rank, n_gpus, hps):
epoch_str = 1
global_step = 0
if hps.pretrainG != "":
if rank == 0:
logger.info("loaded pretrained %s" % (hps.pretrainG))
print(
@ -201,7 +200,6 @@ def run(rank, n_gpus, hps):
)
) ##测试不加载优化器
if hps.pretrainD != "":
if rank == 0:
logger.info("loaded pretrained %s" % (hps.pretrainD))
print(

2
trainset_preprocess_pipeline_print.py
View File

@ -54,7 +54,7 @@ class PreProcess:
def norm_write(self, tmp_audio, idx0, idx1):
tmp_max = np.abs(tmp_audio).max()
if(tmp_max>2.5):
if tmp_max > 2.5:
print("%s-%s-%s-filtered" % (idx0, idx1, tmp_max))
return
tmp_audio = (tmp_audio / tmp_max * (self.max * self.alpha)) + (