Spaces:
Running
Running
import numpy as np | |
import parselmouth | |
from modules.F0Predictor.F0Predictor import F0Predictor | |
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 | |
self.name = "pm" | |
def interpolate_f0(self,f0): | |
''' | |
对F0进行插值处理 | |
''' | |
vuv_vector = np.zeros_like(f0, dtype=np.float32) | |
vuv_vector[f0 > 0.0] = 1.0 | |
vuv_vector[f0 <= 0.0] = 0.0 | |
nzindex = np.nonzero(f0)[0] | |
data = f0[nzindex] | |
nzindex = nzindex.astype(np.float32) | |
time_org = self.hop_length / self.sampling_rate * nzindex | |
time_frame = np.arange(f0.shape[0]) * self.hop_length / self.sampling_rate | |
if data.shape[0] <= 0: | |
return np.zeros(f0.shape[0], dtype=np.float32),vuv_vector | |
if data.shape[0] == 1: | |
return np.ones(f0.shape[0], dtype=np.float32) * f0[0],vuv_vector | |
f0 = np.interp(time_frame, time_org, data, left=data[0], right=data[-1]) | |
return f0,vuv_vector | |
def compute_f0(self,wav,p_len=None): | |
x = wav | |
if p_len is None: | |
p_len = x.shape[0]//self.hop_length | |
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'] | |
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') | |
f0,uv = self.interpolate_f0(f0) | |
return f0 | |
def compute_f0_uv(self,wav,p_len=None): | |
x = wav | |
if p_len is None: | |
p_len = x.shape[0]//self.hop_length | |
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'] | |
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') | |
f0,uv = self.interpolate_f0(f0) | |
return f0,uv | |