PublicMirrors/voice-changer
1
0
Fork 0
mirror of https://github.com/w-okada/voice-changer.git synced 2025-02-02 16:23:58 +03:00
Code Issues Actions Packages Projects Releases Wiki Activity

change weight download process to serialize

Browse Source
This commit is contained in:
wataru 2023-05-03 22:52:00 +09:00
parent 3a4e534091
commit babbc2e9c7
3 changed files with 6 additions and 132 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -41,5 +41,6 @@ client/lib/worklet/dist
docker/cudnn/
server/weights/
server/weights_/
start_trainer.sh

7
server/MMVCServerSIO.py
View File

@ -169,8 +169,11 @@ if __name__ == "MMVCServerSIO":
"position": 1,
}
)
with ThreadPoolExecutor() as pool:
pool.map(download, downloadParams)
# with ThreadPoolExecutor() as pool:
# pool.map(download, downloadParams)
for param in downloadParams:
download(param)
if (
os.path.exists(voiceChangerParams.hubert_base) is False

130
server/voice_changer/RVC/_ModelWrapper.py
View File

@ -1,130 +0,0 @@
import onnxruntime
import torch
import numpy as np
import json
# providers = ['OpenVINOExecutionProvider', "CUDAExecutionProvider", "DmlExecutionProvider", "CPUExecutionProvider"]
providers = ["CPUExecutionProvider"]
class ModelWrapper:
def __init__(self, onnx_model):
self.onnx_model = onnx_model
# ort_options = onnxruntime.SessionOptions()
# ort_options.intra_op_num_threads = 8
self.onnx_session = onnxruntime.InferenceSession(
self.onnx_model, providers=providers
)
# input_info = s
first_input_type = self.onnx_session.get_inputs()[0].type
if first_input_type == "tensor(float)":
self.is_half = False
else:
self.is_half = True
modelmeta = self.onnx_session.get_modelmeta()
try:
metadata = json.loads(modelmeta.custom_metadata_map["metadata"])
self.samplingRate = metadata["samplingRate"]
self.f0 = metadata["f0"]
self.embChannels = metadata["embChannels"]
self.modelType = metadata["modelType"]
self.deprecated = False
self.embedder = (
metadata["embedder"] if "embedder" in metadata else "hubert_base"
)
print(
f"[Voice Changer] Onnx metadata: sr:{self.samplingRate}, f0:{self.f0}, embedder:{self.embedder}"
)
except:
self.samplingRate = 48000
self.f0 = True
self.embChannels = 256
self.modelType = 0
self.deprecated = True
self.embedder = "hubert_base"
print(
"[Voice Changer] ############## !!!! CAUTION !!!! ####################"
)
print(
"[Voice Changer] This onnx's version is depricated. Please regenerate onnxfile. Fallback to default"
)
print(
f"[Voice Changer] Onnx metadata: sr:{self.samplingRate}, f0:{self.f0}"
)
print(
"[Voice Changer] ############## !!!! CAUTION !!!! ####################"
)
def getSamplingRate(self):
return self.samplingRate
def getF0(self):
return self.f0
def getEmbChannels(self):
return self.embChannels
def getModelType(self):
return self.modelType
def getDeprecated(self):
return self.deprecated
def getEmbedder(self):
return self.embedder
def set_providers(self, providers, provider_options=[{}]):
self.onnx_session.set_providers(
providers=providers, provider_options=provider_options
)
def get_providers(self):
return self.onnx_session.get_providers()
def infer_pitchless(self, feats, p_len, sid):
if self.is_half:
audio1 = self.onnx_session.run(
["audio"],
{
"feats": feats.cpu().numpy().astype(np.float16),
"p_len": p_len.cpu().numpy().astype(np.int64),
"sid": sid.cpu().numpy().astype(np.int64),
},
)
else:
audio1 = self.onnx_session.run(
["audio"],
{
"feats": feats.cpu().numpy().astype(np.float32),
"p_len": p_len.cpu().numpy().astype(np.int64),
"sid": sid.cpu().numpy().astype(np.int64),
},
)
return torch.tensor(np.array(audio1))
def infer(self, feats, p_len, pitch, pitchf, sid):
if self.is_half:
audio1 = self.onnx_session.run(
["audio"],
{
"feats": feats.cpu().numpy().astype(np.float16),
"p_len": p_len.cpu().numpy().astype(np.int64),
"pitch": pitch.cpu().numpy().astype(np.int64),
"pitchf": pitchf.cpu().numpy().astype(np.float32),
"sid": sid.cpu().numpy().astype(np.int64),
},
)
else:
audio1 = self.onnx_session.run(
["audio"],
{
"feats": feats.cpu().numpy().astype(np.float32),
"p_len": p_len.cpu().numpy().astype(np.int64),
"pitch": pitch.cpu().numpy().astype(np.int64),
"pitchf": pitchf.cpu().numpy().astype(np.float32),
"sid": sid.cpu().numpy().astype(np.int64),
},
)
return torch.tensor(np.array(audio1))