RVC/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-01-19 18:41:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Format code (#274)

Browse Source 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
This commit is contained in:
github-actions[bot]
2023-05-12 19:43:05 +00:00
committed by GitHub
parent 568378761b
commit af41184320
3 changed files with 90 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
vc_infer_pipeline.py
View File

@@ -2,16 +2,18 @@ import numpy as np, parselmouth, torch, pdb
from time import time as ttime
import torch.nn.functional as F
import scipy.signal as signal
import pyworld, os, traceback, faiss,librosa
import pyworld, os, traceback, faiss, librosa
from scipy import signal
from functools import lru_cache
bh, ah = signal.butter(N=5, Wn=48, btype="high", fs=16000)
input_audio_path2wav={}
input_audio_path2wav = {}
@lru_cache
def cache_harvest_f0(input_audio_path,fs,f0max,f0min,frame_period):
audio=input_audio_path2wav[input_audio_path]
def cache_harvest_f0(input_audio_path, fs, f0max, f0min, frame_period):
audio = input_audio_path2wav[input_audio_path]
f0, t = pyworld.harvest(
audio,
fs=fs,
@@ -22,6 +24,7 @@ def cache_harvest_f0(input_audio_path,fs,f0max,f0min,frame_period):
f0 = pyworld.stonemask(audio, f0, t, fs)
return f0
class VC(object):
def __init__(self, tgt_sr, config):
self.x_pad, self.x_query, self.x_center, self.x_max, self.is_half = (
@@ -41,7 +44,16 @@ class VC(object):
self.t_max = self.sr * self.x_max # 免查询时长阈值
self.device = config.device
def get_f0(self, input_audio_path,x, p_len, f0_up_key, f0_method,filter_radius, inp_f0=None):
def get_f0(
self,
input_audio_path,
x,
p_len,
f0_up_key,
f0_method,
filter_radius,
inp_f0=None,
):
global input_audio_path2wav
time_step = self.window / self.sr * 1000
f0_min = 50
@@ -65,9 +77,9 @@ class VC(object):
f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant"
)
elif f0_method == "harvest":
input_audio_path2wav[input_audio_path]=x.astype(np.double)
f0=cache_harvest_f0(input_audio_path,self.sr,f0_max,f0_min,10)
if(filter_radius>2):
input_audio_path2wav[input_audio_path] = x.astype(np.double)
f0 = cache_harvest_f0(input_audio_path, self.sr, f0_max, f0_min, 10)
if filter_radius > 2:
f0 = signal.medfilt(f0, 3)
f0 *= pow(2, f0_up_key / 12)
# with open("test.txt","w")as f:f.write("\n".join([str(i)for i in f0.tolist()]))
@@ -255,7 +267,15 @@ class VC(object):
sid = torch.tensor(sid, device=self.device).unsqueeze(0).long()
pitch, pitchf = None, None
if if_f0 == 1:
pitch, pitchf = self.get_f0(input_audio_path,audio_pad, p_len, f0_up_key, f0_method,filter_radius, inp_f0)
pitch, pitchf = self.get_f0(
input_audio_path,
audio_pad,
p_len,
f0_up_key,
f0_method,
filter_radius,
inp_f0,
)
pitch = pitch[:p_len]
pitchf = pitchf[:p_len]
if self.device == "mps":
@@ -328,11 +348,11 @@ class VC(object):
)[self.t_pad_tgt : -self.t_pad_tgt]
)
audio_opt = np.concatenate(audio_opt)
if(resample_sr>=16000 and tgt_sr!=resample_sr):
if resample_sr >= 16000 and tgt_sr != resample_sr:
audio_opt = librosa.resample(
audio_opt, orig_sr=tgt_sr, target_sr=resample_sr
)
audio_opt=audio_opt.astype(np.int16)
audio_opt = audio_opt.astype(np.int16)
del pitch, pitchf, sid
if torch.cuda.is_available():
torch.cuda.empty_cache()