kanara/onnx-voice-changer
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

initial commit (clean, no models)

Browse Source
This commit is contained in:
akukanara
2026-05-30 21:30:49 +07:00
Unverified
commit e90b5c971c
22 changed files with 7872 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/infer_pack/modules/F0Predictor/DioF0Predictor.py
+90
View File
@@ -0,0 +1,90 @@
from lib.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
self.f0_min = f0_min
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))
vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
vuv_vector[data > 0.0] = 1.0
vuv_vector[data <= 0.0] = 0.0
ip_data = data
frame_number = data.size
last_value = 0.0
for i in range(frame_number):
if data[i] <= 0.0:
j = i + 1
for j in range(i + 1, frame_number):
if data[j] > 0.0:
break
if j < frame_number - 1:
if last_value > 0.0:
step = (data[j] - data[i - 1]) / float(j - i)
for k in range(i, j):
ip_data[k] = data[i - 1] + step * (k - i + 1)
else:
for k in range(i, j):
ip_data[k] = data[j]
else:
for k in range(i, frame_number):
ip_data[k] = last_value
else:
ip_data[i] = data[i] # 这里可能存在一个没有必要的拷贝
last_value = data[i]
return ip_data[:, 0], vuv_vector[:, 0]
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,
)
res = np.nan_to_num(target)
return res
def compute_f0(self, wav, p_len=None):
if p_len is None:
p_len = wav.shape[0] // self.hop_length
f0, t = pyworld.dio(
wav.astype(np.double),
fs=self.sampling_rate,
f0_floor=self.f0_min,
f0_ceil=self.f0_max,
frame_period=1000 * self.hop_length / self.sampling_rate,
)
f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
for index, pitch in enumerate(f0):
f0[index] = round(pitch, 1)
return self.interpolate_f0(self.resize_f0(f0, p_len))[0]
def compute_f0_uv(self, wav, p_len=None):
if p_len is None:
p_len = wav.shape[0] // self.hop_length
f0, t = pyworld.dio(
wav.astype(np.double),
fs=self.sampling_rate,
f0_floor=self.f0_min,
f0_ceil=self.f0_max,
frame_period=1000 * self.hop_length / self.sampling_rate,
)
f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
for index, pitch in enumerate(f0):
f0[index] = round(pitch, 1)
return self.interpolate_f0(self.resize_f0(f0, p_len))
lib/infer_pack/modules/F0Predictor/F0Predictor.py
+16
View File
@@ -0,0 +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
lib/infer_pack/modules/F0Predictor/HarvestF0Predictor.py
+87
View File
@@ -0,0 +1,87 @@
from lib.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
self.f0_min = f0_min
self.f0_max = f0_max
self.sampling_rate = sampling_rate
self.fs = sampling_rate
def interpolate_f0(self, f0):
"""
对F0进行插值处理
"""
data = np.reshape(f0, (f0.size, 1))
vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
vuv_vector[data > 0.0] = 1.0
vuv_vector[data <= 0.0] = 0.0
ip_data = data
frame_number = data.size
last_value = 0.0
for i in range(frame_number):
if data[i] <= 0.0:
j = i + 1
for j in range(i + 1, frame_number):
if data[j] > 0.0:
break
if j < frame_number - 1:
if last_value > 0.0:
step = (data[j] - data[i - 1]) / float(j - i)
for k in range(i, j):
ip_data[k] = data[i - 1] + step * (k - i + 1)
else:
for k in range(i, j):
ip_data[k] = data[j]
else:
for k in range(i, frame_number):
ip_data[k] = last_value
else:
ip_data[i] = data[i] # 这里可能存在一个没有必要的拷贝
last_value = data[i]
return ip_data[:, 0], vuv_vector[:, 0]
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,
)
res = np.nan_to_num(target)
return res
def compute_f0(self, wav, p_len=None):
if p_len is None:
p_len = wav.shape[0] // self.hop_length
f0, t = pyworld.harvest(
wav.astype(np.double),
fs=self.sampling_rate,
f0_ceil=self.f0_max,
f0_floor=self.f0_min,
frame_period=1000 * self.hop_length / self.sampling_rate,
)
f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
return self.interpolate_f0(self.resize_f0(f0, p_len))[0]
def compute_f0_uv(self, wav, p_len=None):
if p_len is None:
p_len = wav.shape[0] // self.hop_length
f0, t = pyworld.harvest(
wav.astype(np.double),
fs=self.sampling_rate,
f0_floor=self.f0_min,
f0_ceil=self.f0_max,
frame_period=1000 * self.hop_length / self.sampling_rate,
)
f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
return self.interpolate_f0(self.resize_f0(f0, p_len))
lib/infer_pack/modules/F0Predictor/PMF0Predictor.py
+102
View File
@@ -0,0 +1,102 @@
from lib.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
self.f0_min = f0_min
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))
vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
vuv_vector[data > 0.0] = 1.0
vuv_vector[data <= 0.0] = 0.0
ip_data = data
frame_number = data.size
last_value = 0.0
for i in range(frame_number):
if data[i] <= 0.0:
j = i + 1
for j in range(i + 1, frame_number):
if data[j] > 0.0:
break
if j < frame_number - 1:
if last_value > 0.0:
step = (data[j] - data[i - 1]) / float(j - i)
for k in range(i, j):
ip_data[k] = data[i - 1] + step * (k - i + 1)
else:
for k in range(i, j):
ip_data[k] = data[j]
else:
for k in range(i, frame_number):
ip_data[k] = last_value
else:
ip_data[i] = data[i] # 这里可能存在一个没有必要的拷贝
last_value = data[i]
return ip_data[:, 0], vuv_vector[:, 0]
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,
)
res = np.nan_to_num(target)
return res
def compute_f0(self, wav, p_len=None):
x = wav
if p_len is None:
p_len = x.shape[0] // self.hop_length
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_resized = self.resize_f0(f0, p_len)
f0_interpolated, uv = self.interpolate_f0(f0_resized)
return f0_interpolated
def compute_f0_uv(self, wav, p_len=None):
x = wav
if p_len is None:
p_len = x.shape[0] // self.hop_length
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_resized = self.resize_f0(f0, p_len)
f0_interpolated, uv = self.interpolate_f0(f0_resized)
return f0_interpolated, uv
lib/infer_pack/modules/F0Predictor/__init__.py
View File