From 0d9f992fe0d81512f9cf8e8a2255f16bb73173c1 Mon Sep 17 00:00:00 2001
From: Justin John <34035011+justinjohn0306@users.noreply.github.com>
Date: Mon, 19 Jun 2023 19:45:57 -0700
Subject: [PATCH] Delete trainset_preprocess_pipeline_print.py

---
 .../trainset_preprocess_pipeline_print.py     | 139 ------------------
 1 file changed, 139 deletions(-)
 delete mode 100644 voice_conversion/trainset_preprocess_pipeline_print.py

diff --git a/voice_conversion/trainset_preprocess_pipeline_print.py b/voice_conversion/trainset_preprocess_pipeline_print.py
deleted file mode 100644
index 6188c86..0000000
--- a/voice_conversion/trainset_preprocess_pipeline_print.py
+++ /dev/null
@@ -1,139 +0,0 @@
-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
-
-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 = 3.7
-        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)
-            # 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):
-        for path, idx0 in infos:
-            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],)
-                    )
-                    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)