OPENGIT/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2025-05-07 04:09:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add files via upload

Browse Source
This commit is contained in:
Ναρουσέ·μ·γιουμεμί·Χινακάννα 2023-04-24 19:23:00 +08:00 committed by GitHub
parent b63dcf541a
commit 2ee76f8ce0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 404 additions and 1174 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

79
export_onnx.py
View File

@ -1,44 +1,36 @@
from infer_pack.models_onnx_moess import SynthesizerTrnMs256NSFsid from infer_pack.models_onnx import SynthesizerTrnMs256NSFsid
from infer_pack.models_onnx import SynthesizerTrnMs256NSFsidO
import torch import torch
if __name__ == '__main__': person = "Shiroha/shiroha.pth"
MoeVS = True #模型是否为MoeVoiceStudio（原MoeSS）使用 exported_path = "model.onnx"
ModelPath = "Shiroha/shiroha.pth" #模型路径
ExportedPath = "model.onnx" #输出路径
hidden_channels = 256 # hidden_channels，为768Vec做准备
cpt = torch.load(person, map_location="cpu")
cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0] # n_spk
print(*cpt["config"])
test_phone = torch.rand(1, 200, hidden_channels) # hidden unit
test_phone_lengths = torch.tensor([200]).long() # hidden unit 长度（貌似没啥用）
test_pitch = torch.randint(size=(1, 200), low=5, high=255) # 基频（单位赫兹）
test_pitchf = torch.rand(1, 200) # nsf基频
test_ds = torch.LongTensor([0]) # 说话人ID
test_rnd = torch.rand(1, 192, 200) # 噪声（加入随机因子）
device = "cpu" #导出时设备（不影响使用模型） cpt = torch.load(person, map_location="cpu")
cpt["config"][-3]=cpt["weight"]["emb_g.weight"].shape[0]#n_spk
print(*cpt["config"])
net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=False)
net_g.load_state_dict(cpt["weight"], strict=False)
if MoeVS: test_phone = torch.rand(1, 200, 256)
net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=False) # fp32导出（C++要支持fp16必须手动将内存重新排列所以暂时不用fp16） test_phone_lengths = torch.tensor([200]).long()
net_g.load_state_dict(cpt["weight"], strict=False) test_pitch = torch.randint(size=(1 ,200),low=5,high=255)
input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds", "rnd"] test_pitchf = torch.rand(1, 200)
output_names = [ test_ds = torch.LongTensor([0])
"audio", test_rnd = torch.rand(1, 192, 200)
] input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds", "rnd"]
torch.onnx.export( output_names = ["audio", ]
net_g, device="cpu"
torch.onnx.export(net_g,
( (
test_phone.to(device), test_phone.to(device),
test_phone_lengths.to(device), test_phone_lengths.to(device),
test_pitch.to(device), test_pitch.to(device),
test_pitchf.to(device), test_pitchf.to(device),
test_ds.to(device), test_ds.to(device),
test_rnd.to(device), test_rnd.to(device)
), ),
ExportedPath, exported_path,
dynamic_axes={ dynamic_axes={
"phone": [1], "phone": [1],
"pitch": [1], "pitch": [1],
@ -49,33 +41,4 @@ if __name__ == '__main__':
opset_version=16, opset_version=16,
verbose=False, verbose=False,
input_names=input_names, input_names=input_names,
output_names=output_names, output_names=output_names)
)
else:
net_g = SynthesizerTrnMs256NSFsidO(*cpt["config"], is_half=False) # fp32导出（C++要支持fp16必须手动将内存重新排列所以暂时不用fp16）
net_g.load_state_dict(cpt["weight"], strict=False)
input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds"]
output_names = [
"audio",
]
torch.onnx.export(
net_g,
(
test_phone.to(device),
test_phone_lengths.to(device),
test_pitch.to(device),
test_pitchf.to(device),
test_ds.to(device),
),
ExportedPath,
dynamic_axes={
"phone": [1],
"pitch": [1],
"pitchf": [1],
},
do_constant_folding=False,
opset_version=16,
verbose=False,
input_names=input_names,
output_names=output_names,
)

1493
infer-web.py
View File

File diff suppressed because it is too large Load Diff