Mirrors/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2025-12-18 20:49:48 +01:00
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

66
extract_feature_print.py
View File

@@ -1,33 +1,41 @@
import os,sys,traceback
import os, sys, traceback
# device=sys.argv[1]
n_part=int(sys.argv[2])
i_part=int(sys.argv[3])
n_part = int(sys.argv[2])
i_part = int(sys.argv[3])
if len(sys.argv) == 5:
exp_dir=sys.argv[4]
exp_dir = sys.argv[4]
else:
i_gpu=sys.argv[4]
exp_dir=sys.argv[5]
os.environ["CUDA_VISIBLE_DEVICES"]=str(i_gpu)
i_gpu = sys.argv[4]
exp_dir = sys.argv[5]
os.environ["CUDA_VISIBLE_DEVICES"] = str(i_gpu)
import torch
import torch.nn.functional as F
import soundfile as sf
import numpy as np
from fairseq import checkpoint_utils
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
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()
printt(sys.argv)
model_path = "hubert_base.pt"
printt(exp_dir)
wavPath = "%s/1_16k_wavs"%exp_dir
outPath = "%s/3_feature256"%exp_dir
os.makedirs(outPath,exist_ok=True)
wavPath = "%s/1_16k_wavs" % exp_dir
outPath = "%s/3_feature256" % exp_dir
os.makedirs(outPath, exist_ok=True)
# wave must be 16k, hop_size=320
def readwave(wav_path, normalize=False):
wav, sr = sf.read(wav_path)
@@ -41,6 +49,8 @@ def readwave(wav_path, normalize=False):
feats = F.layer_norm(feats, feats.shape)
feats = feats.view(1, -1)
return feats
# HuBERT model
printt("load model(s) from {}".format(model_path))
models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task(
@@ -49,27 +59,32 @@ models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task(
)
model = models[0]
model = model.to(device)
printt("move model to %s"%device)
if device != "cpu": model = model.half()
printt("move model to %s" % device)
if device != "cpu":
model = model.half()
model.eval()
todo=sorted(list(os.listdir(wavPath)))[i_part::n_part]
n = max(1,len(todo) // 10) # 最多打印十条
if(len(todo)==0):printt("no-feature-todo")
todo = sorted(list(os.listdir(wavPath)))[i_part::n_part]
n = max(1, len(todo) // 10) # 最多打印十条
if len(todo) == 0:
printt("no-feature-todo")
else:
printt("all-feature-%s"%len(todo))
for idx,file in enumerate(todo):
printt("all-feature-%s" % len(todo))
for idx, file in enumerate(todo):
try:
if file.endswith(".wav"):
wav_path = "%s/%s"%(wavPath,file)
out_path = "%s/%s"%(outPath,file.replace("wav","npy"))
wav_path = "%s/%s" % (wavPath, file)
out_path = "%s/%s" % (outPath, file.replace("wav", "npy"))
if(os.path.exists(out_path)):continue
if os.path.exists(out_path):
continue
feats = readwave(wav_path, normalize=saved_cfg.task.normalize)
padding_mask = torch.BoolTensor(feats.shape).fill_(False)
inputs = {
"source": feats.half().to(device) if device != "cpu" else feats.to(device),
"source": feats.half().to(device)
if device != "cpu"
else feats.to(device),
"padding_mask": padding_mask.to(device),
"output_layer": 9, # layer 9
}
@@ -78,11 +93,12 @@ else:
feats = model.final_proj(logits[0])
feats = feats.squeeze(0).float().cpu().numpy()
if(np.isnan(feats).sum()==0):
if np.isnan(feats).sum() == 0:
np.save(out_path, feats, allow_pickle=False)
else:
printt("%s-contains nan"%file)
if (idx % n == 0):printt("now-%s,all-%s,%s,%s"%(len(todo),idx,file,feats.shape))
printt("%s-contains nan" % file)
if idx % n == 0:
printt("now-%s,all-%s,%s,%s" % (len(todo), idx, file, feats.shape))
except:
printt(traceback.format_exc())
printt("all-feature-done")