File size: 4,586 Bytes
aef55a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
import sys, os, multiprocessing
from scipy import signal

now_dir = os.getcwd()
sys.path.append(now_dir)

inp_root = sys.argv[1]
sr = int(sys.argv[2])
n_p = int(sys.argv[3])
exp_dir = sys.argv[4]
noparallel = sys.argv[5] == "True"
import numpy as np, os, traceback
from slicer2 import Slicer
import librosa, traceback
from scipy.io import wavfile
import multiprocessing
from my_utils import load_audio
import tqdm

DoFormant = False
Quefrency = 1.0
Timbre = 1.0

mutex = multiprocessing.Lock()
f = open("%s/preprocess.log" % exp_dir, "a+")


def println(strr):
    mutex.acquire()
    print(strr)
    f.write("%s\n" % strr)
    f.flush()
    mutex.release()


class PreProcess:
    def __init__(self, sr, exp_dir):
        self.slicer = Slicer(
            sr=sr,
            threshold=-42,
            min_length=1500,
            min_interval=400,
            hop_size=15,
            max_sil_kept=500,
        )
        self.sr = sr
        self.bh, self.ah = signal.butter(N=5, Wn=48, btype="high", fs=self.sr)
        self.per = 3.0
        self.overlap = 0.3
        self.tail = self.per + self.overlap
        self.max = 0.9
        self.alpha = 0.75
        self.exp_dir = exp_dir
        self.gt_wavs_dir = "%s/0_gt_wavs" % exp_dir
        self.wavs16k_dir = "%s/1_16k_wavs" % exp_dir
        os.makedirs(self.exp_dir, exist_ok=True)
        os.makedirs(self.gt_wavs_dir, exist_ok=True)
        os.makedirs(self.wavs16k_dir, exist_ok=True)

    def norm_write(self, tmp_audio, idx0, idx1):
        tmp_max = np.abs(tmp_audio).max()
        if tmp_max > 2.5:
            print("%s-%s-%s-filtered" % (idx0, idx1, tmp_max))
            return
        tmp_audio = (tmp_audio / tmp_max * (self.max * self.alpha)) + (
            1 - self.alpha
        ) * tmp_audio
        wavfile.write(
            "%s/%s_%s.wav" % (self.gt_wavs_dir, idx0, idx1),
            self.sr,
            tmp_audio.astype(np.float32),
        )
        tmp_audio = librosa.resample(
            tmp_audio, orig_sr=self.sr, target_sr=16000
        )  # , res_type="soxr_vhq"
        wavfile.write(
            "%s/%s_%s.wav" % (self.wavs16k_dir, idx0, idx1),
            16000,
            tmp_audio.astype(np.float32),
        )

    def pipeline(self, path, idx0):
        try:
            audio = load_audio(path, self.sr, DoFormant, Quefrency, Timbre)
            # zero phased digital filter cause pre-ringing noise...
            # audio = signal.filtfilt(self.bh, self.ah, audio)
            audio = signal.lfilter(self.bh, self.ah, audio)

            idx1 = 0
            for audio in self.slicer.slice(audio):
                i = 0
                while 1:
                    start = int(self.sr * (self.per - self.overlap) * i)
                    i += 1
                    if len(audio[start:]) > self.tail * self.sr:
                        tmp_audio = audio[start : start + int(self.per * self.sr)]
                        self.norm_write(tmp_audio, idx0, idx1)
                        idx1 += 1
                    else:
                        tmp_audio = audio[start:]
                        idx1 += 1
                        break
                self.norm_write(tmp_audio, idx0, idx1)
            # println("%s->Suc." % path)
        except:
            println("%s->%s" % (path, traceback.format_exc()))

    def pipeline_mp(self, infos, thread_n):
        for path, idx0 in tqdm.tqdm(
            infos, position=thread_n, leave=True, desc="thread:%s" % thread_n
        ):
            self.pipeline(path, idx0)

    def pipeline_mp_inp_dir(self, inp_root, n_p):
        try:
            infos = [
                ("%s/%s" % (inp_root, name), idx)
                for idx, name in enumerate(sorted(list(os.listdir(inp_root))))
            ]
            if noparallel:
                for i in range(n_p):
                    self.pipeline_mp(infos[i::n_p])
            else:
                ps = []
                for i in range(n_p):
                    p = multiprocessing.Process(
                        target=self.pipeline_mp, args=(infos[i::n_p], i)
                    )
                    ps.append(p)
                    p.start()
                for i in range(n_p):
                    ps[i].join()
        except:
            println("Fail. %s" % traceback.format_exc())


def preprocess_trainset(inp_root, sr, n_p, exp_dir):
    pp = PreProcess(sr, exp_dir)
    println("start preprocess")
    println(sys.argv)
    pp.pipeline_mp_inp_dir(inp_root, n_p)
    println("end preprocess")


if __name__ == "__main__":
    preprocess_trainset(inp_root, sr, n_p, exp_dir)