File size: 3,138 Bytes
ef99749 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 |
from infer_pack.models_onnx_moess import SynthesizerTrnMs256NSFsidM
from infer_pack.models_onnx import SynthesizerTrnMs256NSFsidO
import torch
if __name__ == "__main__":
MoeVS = True # 模型是否为MoeVoiceStudio（原MoeSS）使用
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(ModelPath, 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）
if MoeVS:
net_g = SynthesizerTrnMs256NSFsidM(
*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", "rnd"]
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),
test_rnd.to(device),
),
ExportedPath,
dynamic_axes={
"phone": [1],
"pitch": [1],
"pitchf": [1],
"rnd": [2],
},
do_constant_folding=False,
opset_version=16,
verbose=False,
input_names=input_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,
)
|