OPENGIT
/
Retrieval-based-Voice-Conversion-WebUI
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Format code (#384) 

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
This commit is contained in:
github-actions[bot] 2023-05-30 15:22:53 +08:00 committed by GitHub
parent 5284e38c3d
commit 89afd017ba
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 181 additions and 133 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
infer-web.py
View File

@ -1309,7 +1309,11 @@ with gr.Blocks() as app:
choices=sorted(index_paths),
interactive=True,
)
refresh_button.click(fn=lambda: change_choices()[1], inputs=[], outputs=file_index4)
refresh_button.click(
fn=lambda: change_choices()[1],
inputs=[],
outputs=file_index4,
)
# file_big_npy2 = gr.Textbox(
# label=i18n("特征文件路径"),
# value="E:\\codes\\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",

11
infer_pack/modules/F0Predictor/DioF0Predictor.py
View File

@ -2,6 +2,7 @@ from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
import pyworld
import numpy as np
class DioF0Predictor(F0Predictor):
def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
self.hop_length = hop_length
@ -10,9 +11,9 @@ class DioF0Predictor(F0Predictor):
self.sampling_rate = sampling_rate
def interpolate_f0(self, f0):
'''
"""
对F0进行插值处理
'''
"""
data = np.reshape(f0, (f0.size, 1))
@ -50,7 +51,11 @@ class DioF0Predictor(F0Predictor):
def resize_f0(self, x, target_len):
source = np.array(x)
source[source < 0.001] = np.nan
target = np.interp(np.arange(0, len(source)*target_len, len(source))/ target_len, np.arange(0, len(source)), source)
target = np.interp(
np.arange(0, len(source) * target_len, len(source)) / target_len,
np.arange(0, len(source)),
source,
)
res = np.nan_to_num(target)
return res

8
infer_pack/modules/F0Predictor/F0Predictor.py
View File

@ -1,16 +1,16 @@
class F0Predictor(object):
def compute_f0(self, wav, p_len):
'''
"""
input: wav:[signal_length]
p_len:int
output: f0:[signal_length//hop_length]
'''
"""
pass
def compute_f0_uv(self, wav, p_len):
'''
"""
input: wav:[signal_length]
p_len:int
output: f0:[signal_length//hop_length],uv:[signal_length//hop_length]
'''
"""
pass

11
infer_pack/modules/F0Predictor/HarvestF0Predictor.py
View File

@ -2,6 +2,7 @@ from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
import pyworld
import numpy as np
class HarvestF0Predictor(F0Predictor):
def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
self.hop_length = hop_length
@ -10,9 +11,9 @@ class HarvestF0Predictor(F0Predictor):
self.sampling_rate = sampling_rate
def interpolate_f0(self, f0):
'''
"""
对F0进行插值处理
'''
"""
data = np.reshape(f0, (f0.size, 1))
@ -50,7 +51,11 @@ class HarvestF0Predictor(F0Predictor):
def resize_f0(self, x, target_len):
source = np.array(x)
source[source < 0.001] = np.nan
target = np.interp(np.arange(0, len(source)*target_len, len(source))/ target_len, np.arange(0, len(source)), source)
target = np.interp(
np.arange(0, len(source) * target_len, len(source)) / target_len,
np.arange(0, len(source)),
source,
)
res = np.nan_to_num(target)
return res

40
infer_pack/modules/F0Predictor/PMF0Predictor.py
View File

@ -2,6 +2,7 @@ from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
import parselmouth
import numpy as np
class PMF0Predictor(F0Predictor):
def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
self.hop_length = hop_length
@ -9,11 +10,10 @@ class PMF0Predictor(F0Predictor):
self.f0_max = f0_max
self.sampling_rate = sampling_rate
def interpolate_f0(self, f0):
'''
"""
对F0进行插值处理
'''
"""
data = np.reshape(f0, (f0.size, 1))
@ -55,13 +55,20 @@ class PMF0Predictor(F0Predictor):
else:
assert abs(p_len - x.shape[0] // self.hop_length) < 4, "pad length error"
time_step = self.hop_length / self.sampling_rate * 1000
f0 = parselmouth.Sound(x, self.sampling_rate).to_pitch_ac(
time_step=time_step / 1000, voicing_threshold=0.6,
pitch_floor=self.f0_min, pitch_ceiling=self.f0_max).selected_array['frequency']
f0 = (
parselmouth.Sound(x, self.sampling_rate)
.to_pitch_ac(
time_step=time_step / 1000,
voicing_threshold=0.6,
pitch_floor=self.f0_min,
pitch_ceiling=self.f0_max,
)
.selected_array["frequency"]
)
pad_size = (p_len - len(f0) + 1) // 2
if(pad_size>0 or p_len - len(f0) - pad_size>0):
f0 = np.pad(f0,[[pad_size,p_len - len(f0) - pad_size]], mode='constant')
if pad_size > 0 or p_len - len(f0) - pad_size > 0:
f0 = np.pad(f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant")
f0, uv = self.interpolate_f0(f0)
return f0
@ -72,12 +79,19 @@ class PMF0Predictor(F0Predictor):
else:
assert abs(p_len - x.shape[0] // self.hop_length) < 4, "pad length error"
time_step = self.hop_length / self.sampling_rate * 1000
f0 = parselmouth.Sound(x, self.sampling_rate).to_pitch_ac(
time_step=time_step / 1000, voicing_threshold=0.6,
pitch_floor=self.f0_min, pitch_ceiling=self.f0_max).selected_array['frequency']
f0 = (
parselmouth.Sound(x, self.sampling_rate)
.to_pitch_ac(
time_step=time_step / 1000,
voicing_threshold=0.6,
pitch_floor=self.f0_min,
pitch_ceiling=self.f0_max,
)
.selected_array["frequency"]
)
pad_size = (p_len - len(f0) + 1) // 2
if(pad_size>0 or p_len - len(f0) - pad_size>0):
f0 = np.pad(f0,[[pad_size,p_len - len(f0) - pad_size]], mode='constant')
if pad_size > 0 or p_len - len(f0) - pad_size > 0:
f0 = np.pad(f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant")
f0, uv = self.interpolate_f0(f0)
return f0, uv

56
infer_pack/onnx_inference.py
View File

@ -3,13 +3,14 @@ import librosa
import numpy as np
import soundfile
class ContentVec():
class ContentVec:
def __init__(self, vec_path="pretrained/vec-768-layer-12.onnx", device=None):
print("load model(s) from {}".format(vec_path))
if device == 'cpu' or device is None:
providers = ['CPUExecutionProvider']
elif device == 'cuda':
providers = ['CUDAExecutionProvider', 'CPUExecutionProvider']
if device == "cpu" or device is None:
providers = ["CPUExecutionProvider"]
elif device == "cuda":
providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
else:
raise RuntimeError("Unsportted Device")
self.model = onnxruntime.InferenceSession(vec_path, providers=providers)
@ -31,33 +32,42 @@ class ContentVec():
def get_f0_predictor(f0_predictor, hop_length, sampling_rate, **kargs):
if f0_predictor == "pm":
from infer_pack.modules.F0Predictor.PMF0Predictor import PMF0Predictor
f0_predictor_object = PMF0Predictor(hop_length=hop_length,sampling_rate=sampling_rate)
f0_predictor_object = PMF0Predictor(
hop_length=hop_length, sampling_rate=sampling_rate
)
elif f0_predictor == "harvest":
from infer_pack.modules.F0Predictor.HarvestF0Predictor import HarvestF0Predictor
f0_predictor_object = HarvestF0Predictor(hop_length=hop_length,sampling_rate=sampling_rate)
f0_predictor_object = HarvestF0Predictor(
hop_length=hop_length, sampling_rate=sampling_rate
)
elif f0_predictor == "dio":
from infer_pack.modules.F0Predictor.DioF0Predictor import DioF0Predictor
f0_predictor_object = DioF0Predictor(hop_length=hop_length,sampling_rate=sampling_rate)
f0_predictor_object = DioF0Predictor(
hop_length=hop_length, sampling_rate=sampling_rate
)
else:
raise Exception("Unknown f0 predictor")
return f0_predictor_object
class OnnxRVC():
class OnnxRVC:
def __init__(
self,
model_path,
sr=40000,
hop_size=512,
vec_path="vec-768-layer-12",
device="cpu"
device="cpu",
):
vec_path = f"pretrained/{vec_path}.onnx"
self.vec_model = ContentVec(vec_path, device)
if device == 'cpu' or device is None:
providers = ['CPUExecutionProvider']
elif device == 'cuda':
providers = ['CUDAExecutionProvider', 'CPUExecutionProvider']
if device == "cpu" or device is None:
providers = ["CPUExecutionProvider"]
elif device == "cuda":
providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
else:
raise RuntimeError("Unsportted Device")
self.model = onnxruntime.InferenceSession(model_path, providers=providers)
@ -71,11 +81,19 @@ class OnnxRVC():
self.model.get_inputs()[2].name: pitch,
self.model.get_inputs()[3].name: pitchf,
self.model.get_inputs()[4].name: ds,
self.model.get_inputs()[5].name: rnd
self.model.get_inputs()[5].name: rnd,
}
return (self.model.run(None, onnx_input)[0] * 32767).astype(np.int16)
def inference(self, raw_path, sid, f0_method="dio", f0_up_key=0, pad_time=0.5, cr_threshold=0.02):
def inference(
self,
raw_path,
sid,
f0_method="dio",
f0_up_key=0,
pad_time=0.5,
cr_threshold=0.02,
):
f0_min = 50
f0_max = 1100
f0_mel_min = 1127 * np.log(1 + f0_min / 700)
@ -84,11 +102,11 @@ class OnnxRVC():
f0_method,
hop_length=self.hop_size,
sampling_rate=self.sampling_rate,
threshold=cr_threshold
threshold=cr_threshold,
)
wav, sr = librosa.load(raw_path, sr=self.sampling_rate)
org_length = len(wav)
if org_length / sr > 50.:
if org_length / sr > 50.0:
raise RuntimeError("Reached Max Length")
wav16k = librosa.resample(wav, orig_sr=self.sampling_rate, target_sr=16000)
@ -117,5 +135,5 @@ class OnnxRVC():
hubert_length = np.array([hubert_length]).astype(np.int64)
out_wav = self.forward(hubert, hubert_length, pitch, pitchf, ds, rnd).squeeze()
out_wav = np.pad(out_wav, (0, 2*self.hop_size), 'constant')
out_wav = np.pad(out_wav, (0, 2 * self.hop_size), "constant")
return out_wav[0:org_length]

4
onnx_inference_demo.py
View File

@ -11,7 +11,9 @@ vec_name = "vec-256-layer-9" #内部自动补齐为 f"pretrained/{vec_name}.onnx
wav_path = "123.wav" # 输入路径或ByteIO实例
out_path = "out.wav" # 输出路径或ByteIO实例
model = OnnxRVC(model_path, vec_path=vec_name, sr=sampling_rate, hop_size=hop_size, device="cuda")
model = OnnxRVC(
model_path, vec_path=vec_name, sr=sampling_rate, hop_size=hop_size, device="cuda"
)
audio = model.inference(wav_path, sid, f0_method=f0_method, f0_up_key=f0_up_key)