Page MenuHomePhabricator
Files F4880267

No OneTemporary
Actions

View Options

diff --git a/AutoCoverTool/script/inference_one.py b/AutoCoverTool/script/inference_one.py
index 8aace4c..3565bec 100644
--- a/AutoCoverTool/script/inference_one.py
+++ b/AutoCoverTool/script/inference_one.py
@@ -1,1529 +1,1529 @@
"""
单个处理的逻辑
song_id:
---src.mp3 // 源数据，需要提前放进去
---cache
---vocal.wav // 分离之后产生
---acc.wav // 分离之后产生
---vocal_32.wav // 分离之后产生
---song_id_sp1.wav // 合成之后产生
---song_id_sp2.wav // 合成之后产生
---song_id_sp2_d.wav // 降噪之后生成
---song_id_sp2_dv.wav // 降噪+拉伸之后产生 [占比太高的不产生]
---song_id_sp2_dve442.wav // 手动调整之后产生
---song_id_sp2_dve442_replace.wav // 替换之后产生
---song_id_sp2_dve442_replace_mix.wav // 人声+伴奏混合之后产生
---song_id
--acc.mp3 // 44k双声道320k
--vocal.mp3 // 44k双声道320k
--src.mp3 // 44k双声道320k
--song_id_sp2_dv.mp3 // 44k单声道320k
---song_id_out // 对外输出
--src.mp3 // 原始音频
--song_id_sp2_dv_replace_mix.mp3 // 制作完成的音频
环境安装:
conda create -n auto_song_cover python=3.9
# 安装demucs环境[进入到ref.music_remover 执行pip install -r requirements.txt]
# 安装so_vits_svc环境[进入到ref.so_vits_svc 执行pip install -r requirements.txt]
pip install librosa
pip install scikit-maad
pip install praat-parselmouth
pip install matplotlib
pip install torchvision
pip install madmom
pip install torchstat
环境设置:
export PATH=$PATH:/data/gpu_env_common/env/bin/ffmpeg/bin
export PYTHONPATH=$PWD:$PWD/ref/music_remover/demucs:$PWD/ref/so_vits_svc:$PWD/ref/split_dirty_frame
"""
import os
import time
import shutil
import random
import logging
import librosa
gs_err_code_success = 0
gs_err_code_no_src_mp3 = 1
gs_err_code_separate = 2
gs_err_code_trans_32 = 3
gs_err_code_encode_err = 4
gs_err_code_replace_err = 5
gs_err_code_replace_trans_err = 6
gs_err_code_mix_err = 7
gs_err_code_mix_transcode_err = 8
gs_err_code_no_src_dir = 9
gs_err_code_volume_err = 10
gs_err_code_trans2_442 = 11
gs_err_code_reverb = 12
gs_denoise_exe = "/opt/soft/bin/denoise_exe"
gs_draw_volume_exe = "/opt/soft/bin/draw_volume_v1"
gs_simple_mixer_path = "/opt/soft/bin/simple_mixer"
gs_rever_path = "/data/rsync/jianli.yang/dereverbrate/build/dereverbrate_test"
from ref.music_remover.separate_interface import SeparateInterface
from ref.so_vits_svc.inference_main import *
from ref.split_dirty_frame.script.process_one import ReplaceVocalFrame, construct_power_fragment
from ref.split_dirty_frame.dataset.dataset import file2mfcc
class SongCoverInference:
def __init__(self):
self.work_dir = None
self.cache_dir = None
self.cid = None
self.src_mp3 = None
self.vocal_path = None
self.vocal_32_path = None
self.acc_path = None
self.speakers = [
10414574138721494,
10414574140317353,
1688849864840588,
3634463651,
5629499489839033,
5910973794723621,
6755399374234747,
8162774327817435,
8162774329368194,
1125899914308640, # 以下为男声,包括这个
12384898975368914,
12947848931397021,
3096224748076687,
3096224751151928,
5066549357604730,
5348024335101054,
6755399442719465,
7036874421386111
]
self.speakers_model_path = "data/train_users/{}/logs/32k/G_2000.pth"
self.speakers_model_config = "data/train_users/{}/config/config.json"
st = time.time()
self.separate_inst = SeparateInterface()
self.replace_vocal_frame_inst = ReplaceVocalFrame("data/models/split_dirty_frame_v5_3_epoch3_852.pth")
logging.info("SongCoverInference init sp={}".format(time.time() - st))
def separate(self, cid, src_mp3, vocal_path, acc_path):
"""
人声伴奏分离
:param cid:
:param src_mp3:
:param vocal_path:
:param acc_path:
:return:
"""
st = time.time()
if not self.separate_inst.process(cid, src_mp3, vocal_path, acc_path):
return gs_err_code_separate
if not os.path.exists(vocal_path) or not os.path.exists(acc_path):
return gs_err_code_separate
# 转码出一个32k单声道的数据
cmd = "ffmpeg -i {} -ar 32000 -ac 1 -y {} -loglevel fatal".format(vocal_path, self.vocal_32_path)
os.system(cmd)
if not os.path.exists(self.vocal_32_path):
return gs_err_code_trans_32
print("separate:cid={}|sp={}".format(cid, time.time() - st))
return gs_err_code_success
def get_start_ms(self, vocal_path):
"""
给定原始音频，找一段连续10s的音频
:param vocal_path:
:return:
"""
audio, sr = librosa.load(vocal_path, sr=16000)
audio = librosa.util.normalize(audio)
# 帧长100ms,帧移10ms,计算能量
power_arr = []
for i in range(0, len(audio) - 1600, 160):
power_arr.append(np.sum(np.abs(audio[i:i + 160])) / 160)
# 将能量小于等于10的部分做成段
power_arr = construct_power_fragment(power_arr)
fragments = []
last_pos = 0
for idx, line in enumerate(power_arr):
start = round(float(line[0]) * 0.01, 3)
duration = round(float(line[1]) * 0.01, 3)
fragments.append([last_pos, start - last_pos])
last_pos = start + duration
if last_pos < len(audio) / sr:
fragments.append([last_pos, len(audio) / sr - last_pos])
# 合并数据，两者间隔在50ms以内的合并起来
idx = 0
while idx < len(fragments) - 1:
if fragments[idx + 1][0] - (fragments[idx][0] + fragments[idx][1]) < 0.05:
fragments[idx][1] = fragments[idx + 1][0] + fragments[idx + 1][1] - fragments[idx][0]
del fragments[idx + 1]
idx -= 1
idx += 1
# out_file = vocal_path + "_power.csv"
# with open(out_file, "w") as f:
# f.write("Name\tStart\tDuration\tTime Format\tType\n")
# for fragment in fragments:
# start = round(float(fragment[0]), 3)
# duration = round(float(fragment[1]), 3)
# strr = "{}\t{}\t{}\t{}\n".format("11", start, duration, "decimal\tCue\t")
# f.write(strr)
# 筛选出开始的位置
# 1. 连续时长大于10s，当前段长度大于3s
# 2. 不可用
# 从0到fragments[idx], 包含idx其中人声段的总和
tot_vocal_duration = [fragments[0][1]]
for i in range(1, len(fragments)):
tot_vocal_duration.append(tot_vocal_duration[i - 1] + fragments[i][1])
# 计算出任意两段之间非人声占比
for i in range(0, len(fragments)):
if fragments[i][1] >= 3:
now_tot = 0
if i > 0:
now_tot = tot_vocal_duration[i - 1]
for j in range(i + 1, len(fragments)):
cur_rate = tot_vocal_duration[j] - now_tot
cur_rate = cur_rate / (fragments[j][1] + fragments[j][0] - fragments[i][0])
if cur_rate > 0.1:
return fragments[i][0]
return -1
def inference_speaker(self):
"""
推理生成合成后的音频
随机取5个干声,选择占比最小的，并且要求占比小于0.3
:return:
"""
st = time.time()
out_speakers = random.sample(self.speakers, 5)
out_songs_dict = {}
for speaker in out_speakers:
model_path = self.speakers_model_path.format(speaker)
config_path = self.speakers_model_config.format(speaker)
song_path = os.path.join(self.cache_dir, "{}_{}.wav".format(self.cid, speaker))
try:
inf(model_path, config_path, self.vocal_32_path, song_path, "prod")
except Exception as ex:
logging.info("cid={}, inference_speaker err={}".format(self.cid, ex))
continue
if os.path.exists(song_path):
rate = self.replace_vocal_frame_inst.get_rate(song_path)
if rate < 0.3:
out_songs_dict[song_path] = rate
# 从内部选择占比最低的
out_songs = []
if len(out_songs_dict.keys()) > 0:
st_sec = self.get_start_ms(self.vocal_path)
song_msg = sorted(out_songs_dict.items(), key=lambda kv: kv[1])[0]
out_songs = [song_msg[0]]
logging.info("GetRate:cid={},song={},rate={},st_tm={}".format(self.cid, song_msg[0], round(song_msg[1], 2),
round(st_sec, 3)))
print("GetRate:cid={},song={},rate={},st_tm={}".format(self.cid, song_msg[0], round(song_msg[1], 2),
round(st_sec, 3)))
# logging.info("inference_speaker len = {} finish sp = {}".format(len(out_songs), time.time() - st))
print("inference_speaker len = {} finish sp = {}".format(len(out_songs), time.time() - st))
return out_songs
def get_new_vocal_rate(self, songs):
"""
获取人声的比率
:param songs:
:return:
"""
st = time.time()
need_to_process_song = []
for song in songs:
rate = self.replace_vocal_frame_inst.get_rate(song)
logging.info("{} {} replace_rate={}".format(self.cid, song, rate))
if rate < 1.0:
need_to_process_song.append(song)
logging.info(
"get_new_vocal_rate belen = {} len = {} finish sp = {}".format(len(songs), len(need_to_process_song),
time.time() - st))
return need_to_process_song
def preprocess_vocal(self, songs, vocal_path):
"""
1. 降噪
2. 拉伸
:param songs:
:param vocal_path: 参考的音频信号
:return:
"""
st = time.time()
dv_out_list = []
for song in songs:
denoise_path = str(song).replace(".wav", "_d.wav")
cmd = "{} {} {}".format(gs_denoise_exe, song, denoise_path)
os.system(cmd)
if not os.path.exists(denoise_path):
print("{} {} ERROR denoise".format(self.cid, song))
continue
# 拉伸
volume_path = str(song).replace(".wav", "_dv.wav")
cmd = "{} {} {} {}".format(gs_draw_volume_exe, denoise_path, vocal_path, volume_path)
os.system(cmd)
if not os.path.exists(volume_path):
print("{} {} ERROR denoise".format(self.cid, volume_path))
continue
dv_out_list.append(volume_path)
print(
"preprocess_vocal belen = {} len = {} finish sp = {}".format(len(songs), len(dv_out_list),
time.time() - st))
return dv_out_list
def output(self, dv_out_list):
"""
对外输出数据
:param dv_out_list:
:return:
"""
st = time.time()
out_dir = os.path.join(self.work_dir, self.cid)
if os.path.exists(out_dir):
shutil.rmtree(out_dir)
os.makedirs(out_dir)
# 拷贝数据
dst_mp3_path = os.path.join(out_dir, "src_mp3")
dst_acc_path = os.path.join(out_dir, "acc.mp3")
dst_vocal_path = os.path.join(out_dir, "vocal.mp3")
shutil.copyfile(self.src_mp3, dst_mp3_path)
cmd = "ffmpeg -i {} -ab 320k -y {} -loglevel fatal".format(self.acc_path, dst_acc_path)
os.system(cmd)
if not os.path.exists(dst_acc_path):
return gs_err_code_encode_err
cmd = "ffmpeg -i {} -ab 320k -y {} -loglevel fatal".format(self.vocal_path, dst_vocal_path)
os.system(cmd)
if not os.path.exists(dst_vocal_path):
return gs_err_code_encode_err
# 将所有数据放到out_dir中，用于给人工标注
for dv_wav in dv_out_list:
dv_wav_name = str(dv_wav).split("/")[-1].replace(".wav", "_441.mp3")
dst_dv_path = os.path.join(out_dir, dv_wav_name)
cmd = "ffmpeg -i {} -ar 44100 -ac 1 -ab 320k -y {} -loglevel fatal".format(dv_wav, dst_dv_path)
os.system(cmd)
if not os.path.exists(dst_dv_path):
print("{} encode err!".format(cmd))
continue
logging.info(
"preprocess_vocal output sp = {}".format(time.time() - st))
def process_one(self, cid, work_dir, enable_output=False):
logging.info("\nstart:cid={},work_dir={}----------------------->>>>>>>>".format(cid, work_dir))
self.cid = cid
self.work_dir = work_dir
# 所有不对外交付的，全部放到这里
self.cache_dir = os.path.join(work_dir, "cache")
if os.path.exists(self.cache_dir):
shutil.rmtree(self.cache_dir)
os.makedirs(self.cache_dir)
self.src_mp3 = os.path.join(self.work_dir, "src.mp3")
if not os.path.exists(self.src_mp3):
return gs_err_code_no_src_mp3
self.vocal_path = os.path.join(self.cache_dir, "vocal.wav")
self.vocal_32_path = os.path.join(self.cache_dir, "vocal_32.wav")
self.acc_path = os.path.join(self.cache_dir, "acc.wav")
if not os.path.exists(self.vocal_32_path):
logging.info("start separate ... {} {} {}".format(self.src_mp3, self.vocal_path, self.acc_path))
err = self.separate(cid, self.src_mp3, self.vocal_path, self.acc_path)
if err != gs_err_code_success:
return err
logging.info("start inference_speaker ...")
out_songs = self.inference_speaker()
logging.info("start get_new_vocal_rate ...")
# out_songs = self.get_new_vocal_rate(out_songs)
dv_out_list = self.preprocess_vocal(out_songs, self.vocal_path)
if enable_output:
self.output(dv_out_list)
else:
# 默认全部处理一遍
for dv_out_path in dv_out_list:
src_path = dv_out_path.replace("_dv.wav", ".wav")
err = self.after_process(self.cid, self.work_dir, src_path, dv_out_path, self.vocal_path, self.acc_path,
True, True)
if err != 0:
logging.info("after_process err {}".format(err))
logging.info("finish:cid={},work_dir={}----------------------->>>>>>>>".format(cid, work_dir))
return gs_err_code_success
def reverb_by_vocal(self, file):
st = time.time()
file_442 = file.replace(".wav", "_442.wav")
if not os.path.exists(file_442):
cmd = "ffmpeg -i {} -ar 44100 -ac 2 -y {}".format(file, file_442)
os.system(cmd)
if not os.path.exists(file_442):
return None, gs_err_code_trans2_442
file_dst = file.replace(".wav", "_442_dr.wav")
cmd = "{} {} {} {}".format(gs_rever_path, self.vocal_path, file_442, file_dst)
os.system(cmd)
if not os.path.exists(file_dst):
return None, gs_err_code_reverb
print("cid = {}, reverb_by_vocal sp={}".format(self.cid, time.time() - st))
return file_dst, gs_err_code_success
def after_process(self, cid, work_dir, in_file, effect_file, vocal_file, acc_file, need_draw=True,
need_reverb=True):
"""
后处理逻辑
将处理好的音频进行替换，然后和伴奏进行混合，最后进行编码
:return:
"""
if need_reverb:
# 抓取混响
effect_file, err = self.reverb_by_vocal(in_file)
if err != gs_err_code_success:
return err
if need_draw:
# 增加一个拉伸的步骤
volume_path = str(effect_file).replace(".wav", "_dv.wav")
cmd = "{} {} {} {}".format(gs_draw_volume_exe, effect_file, vocal_file, volume_path)
print(cmd)
os.system(cmd)
if not os.path.exists(volume_path):
print("{} {} ERROR draw volume".format(self.cid, volume_path))
return gs_err_code_volume_err
effect_file = volume_path
st = time.time()
self.cid = cid
self.work_dir = work_dir
self.src_mp3 = os.path.join(self.work_dir, "src.mp3")
if not os.path.exists(self.work_dir):
return gs_err_code_no_src_dir
self.replace_vocal_frame_inst.process(in_file, effect_file, vocal_file)
dst_path = effect_file + "_replace.wav"
if not os.path.exists(dst_path):
return gs_err_code_replace_err
print("replace_vocal_frame_inst sp = {}".format(time.time() - st))
# 转码
dst_path_442 = dst_path.replace("_replace.wav", "_replace442.wav")
cmd = "ffmpeg -i {} -ar 44100 -ac 2 -y {} -loglevel fatal".format(dst_path, dst_path_442)
os.system(cmd)
if not os.path.exists(dst_path_442):
return gs_err_code_replace_trans_err
# 合并转码后再做一次拉伸，保证响度
volume_path = str(dst_path_442).replace(".wav", "_dv.wav")
cmd = "{} {} {} {}".format(gs_draw_volume_exe, dst_path_442, vocal_file, volume_path)
print(cmd)
os.system(cmd)
if not os.path.exists(volume_path):
print("{} {} ERROR draw volume".format(self.cid, volume_path))
return gs_err_code_volume_err
dst_path_442 = volume_path
# 混合
mix_path = dst_path_442.replace("_replace442.wav", "_replace442_mix.wav")
cmd = "{} {} {} {}".format(gs_simple_mixer_path, dst_path_442, acc_file, mix_path)
print("{}".format(cmd))
os.system(cmd)
if not os.path.exists(mix_path):
return gs_err_code_mix_err
# 编码为mp3
output_dir = os.path.join(self.work_dir, self.cid + "_out")
if not os.path.exists(output_dir):
os.makedirs(output_dir)
name = str(mix_path).replace("_replace442_mix.wav", "_replace442_mix.mp3").split("/")[-1]
mix_path_mp3 = os.path.join(output_dir, name)
cmd = "ffmpeg -i {} -ab 320k -y {} -loglevel fatal".format(mix_path, mix_path_mp3)
os.system(cmd)
if not os.path.exists(mix_path_mp3):
return gs_err_code_mix_transcode_err
# 拷贝src到output_dir
# shutil.copyfile(self.src_mp3, os.path.join(output_dir, "src.mp3"))
# logging.info("after_process sp = {}".format(time.time() - st))
return gs_err_code_success
def test_volume_dir():
base_dir = "/data/rsync/jianli.yang/AutoCoverTool/data/inf_users/me_3_w4"
# arr = [
# "611752105015523266/cache/611752105015523266_5066549357604730.wav",
# "611752105017233541/cache/611752105017233541_6755399442719465.wav",
# "611752105030414513/cache/611752105030414513_1125899914308640.wav",
# "611752105030414549/cache/611752105030414549_5066549357604730.wav",
# "611752105030414557/cache/611752105030414557_8162774327817435.wav",
# "611752105030414588/cache/611752105030414588_1125899914308640.wav",
# "611752105030414597/cache/611752105030414597_6755399374234747.wav",
# "611752105030414613/cache/611752105030414613_5066549357604730.wav",
# "611752105030414615/cache/611752105030414615_1125899914308640.wav",
# "611752105030414619/cache/611752105030414619_5066549357604730.wav",
# "611752105030414633/cache/611752105030414633_8162774327817435.wav",
# "611752105030414638/cache/611752105030414638_8162774329368194.wav",
# "611752105030414689/cache/611752105030414689_8162774327817435.wav",
# "611752105030414702/cache/611752105030414702_6755399374234747.wav",
# "611752105030414742/cache/611752105030414742_5066549357604730.wav",
# "611752105030414763/cache/611752105030414763_1125899914308640.wav",
# "611752105030414773/cache/611752105030414773_8162774329368194.wav",
# "611752105030414777/cache/611752105030414777_8162774329368194.wav",
# "611752105030414779/cache/611752105030414779_1125899914308640.wav",
# "611752105030414784/cache/611752105030414784_6755399442719465.wav",
# "611752105030414890/cache/611752105030414890_5066549357604730.wav",
# "611752105030414915/cache/611752105030414915_5066549357604730.wav",
# "611752105030414925/cache/611752105030414925_1125899914308640.wav",
# "611752105030414929/cache/611752105030414929_1125899914308640.wav",
# "611752105030414935/cache/611752105030414935_3634463651.wav",
# "611752105030414943/cache/611752105030414943_6755399374234747.wav",
# "611752105030414957/cache/611752105030414957_12384898975368914.wav",
# "611752105030414962/cache/611752105030414962_8162774327817435.wav",
# "611752105030414976/cache/611752105030414976_10414574138721494.wav",
# "611752105030414993/cache/611752105030414993_12947848931397021.wav",
# "611752105030414995/cache/611752105030414995_5066549357604730.wav",
# "611752105030415003/cache/611752105030415003_12947848931397021.wav",
# "611752105030415014/cache/611752105030415014_10414574138721494.wav",
# "611752105030415018/cache/611752105030415018_8162774329368194.wav",
# "611752105030415032/cache/611752105030415032_6755399442719465.wav",
# "611752105030415056/cache/611752105030415056_3096224748076687.wav",
# "611752105030415067/cache/611752105030415067_1125899914308640.wav",
# "611752105030415071/cache/611752105030415071_5910973794723621.wav",
# "611752105030415074/cache/611752105030415074_1125899914308640.wav",
# "611752105030415083/cache/611752105030415083_1125899914308640.wav",
# "611752105030415087/cache/611752105030415087_5910973794723621.wav",
# "611752105030415100/cache/611752105030415100_10414574138721494.wav",
# "611752105030415103/cache/611752105030415103_8162774329368194.wav"
# ]
# arr = [
# "611752105020256284/cache/611752105020256284_8162774329368194.wav",
# "611752105020286433/cache/611752105020286433_1125899914308640.wav",
# "611752105020286443/cache/611752105020286443_12384898975368914.wav",
# "611752105020286446/cache/611752105020286446_5629499489839033.wav",
# "611752105020290639/cache/611752105020290639_3634463651.wav",
# "611752105020290695/cache/611752105020290695_1125899914308640.wav",
# "611752105020315328/cache/611752105020315328_8162774329368194.wav",
# "611752105020315368/cache/611752105020315368_1688849864840588.wav",
# "611752105020336950/cache/611752105020336950_3634463651.wav",
# "611752105020343687/cache/611752105020343687_8162774327817435.wav",
# "611752105020343699/cache/611752105020343699_1125899914308640.wav",
# "611752105020351134/cache/611752105020351134_10414574138721494.wav",
# "611752105020357112/cache/611752105020357112_8162774327817435.wav",
# "611752105020378620/cache/611752105020378620_8162774327817435.wav",
# "611752105020387015/cache/611752105020387015_1125899914308640.wav",
# "611752105020394121/cache/611752105020394121_1125899914308640.wav",
# "611752105020394297/cache/611752105020394297_3634463651.wav",
# "611752105020411654/cache/611752105020411654_3096224751151928.wav",
# "611752105020417688/cache/611752105020417688_12947848931397021.wav",
# "611752105020563523/cache/611752105020563523_8162774327817435.wav",
# "611752105021332759/cache/611752105021332759_3634463651.wav",
# "611752105022446809/cache/611752105022446809_8162774327817435.wav",
# "611752105022647082/cache/611752105022647082_8162774327817435.wav",
# "611752105022667231/cache/611752105022667231_8162774327817435.wav",
# "611752105022735101/cache/611752105022735101_5066549357604730.wav",
# "611752105022736204/cache/611752105022736204_1125899914308640.wav",
# "611752105022745595/cache/611752105022745595_10414574138721494.wav",
# "611752105022770952/cache/611752105022770952_1125899914308640.wav",
# "611752105022842004/cache/611752105022842004_3634463651.wav",
# "611752105022842477/cache/611752105022842477_1125899914308640.wav",
# "611752105023434557/cache/611752105023434557_6755399374234747.wav",
# "611752105023532439/cache/611752105023532439_8162774329368194.wav",
# "611752105023623965/cache/611752105023623965_3096224748076687.wav",
# "611752105024250202/cache/611752105024250202_8162774327817435.wav",
# "611752105024628047/cache/611752105024628047_5066549357604730.wav",
# "611752105024676794/cache/611752105024676794_6755399442719465.wav",
# "611752105024678976/cache/611752105024678976_6755399442719465.wav",
# "611752105024679221/cache/611752105024679221_8162774329368194.wav",
# "611752105024953316/cache/611752105024953316_1688849864840588.wav",
# "611752105025104181/cache/611752105025104181_6755399374234747.wav",
# "611752105026189342/cache/611752105026189342_5910973794723621.wav",
# "611752105026523547/cache/611752105026523547_1125899914308640.wav",
# "611752105026707760/cache/611752105026707760_3096224748076687.wav",
# "611752105026771723/cache/611752105026771723_8162774327817435.wav",
# "611752105026946178/cache/611752105026946178_10414574140317353.wav",
# "611752105027047993/cache/611752105027047993_5066549357604730.wav",
# "611752105027188746/cache/611752105027188746_5066549357604730.wav",
# "611752105027189453/cache/611752105027189453_8162774329368194.wav",
# "611752105027302268/cache/611752105027302268_5066549357604730.wav",
# "611752105027557408/cache/611752105027557408_1125899914308640.wav",
# "611752105028650636/cache/611752105028650636_8162774327817435.wav",
# "611752105028683824/cache/611752105028683824_1125899914308640.wav",
# "611752105029990849/cache/611752105029990849_7036874421386111.wav",
# "611752105029993297/cache/611752105029993297_6755399374234747.wav",
# "611752105030077711/cache/611752105030077711_3096224748076687.wav",
# "611752105030104548/cache/611752105030104548_5629499489839033.wav",
# "611752105030419624/cache/611752105030419624_8162774327817435.wav",
# "611752105030419633/cache/611752105030419633_1125899914308640.wav",
# "611752105030419688/cache/611752105030419688_1125899914308640.wav",
# "611752105030433779/cache/611752105030433779_3634463651.wav"
# ]
arr = [
"611752105020256284/cache/611752105020256284_8162774329368194.wav",
"611752105020286433/cache/611752105020286433_1125899914308640.wav",
"611752105020286443/cache/611752105020286443_12384898975368914.wav",
"611752105020286446/cache/611752105020286446_5629499489839033.wav",
"611752105020290639/cache/611752105020290639_3634463651.wav",
"611752105020290695/cache/611752105020290695_1125899914308640.wav",
"611752105020315328/cache/611752105020315328_8162774329368194.wav",
"611752105020315368/cache/611752105020315368_1688849864840588.wav",
"611752105020336950/cache/611752105020336950_3634463651.wav",
"611752105020343687/cache/611752105020343687_8162774327817435.wav"
]
s_inst = SongCoverInference()
for vocal_file in arr:
sstime = time.time()
i_file = os.path.join(base_dir, vocal_file)
cur_dir = "/".join(i_file.split("/")[:-1])
# e_file = os.path.join(base_dir, vocal_file.replace(".wav", "_dev_441.wav"))
# e_file = os.path.join(base_dir, vocal_file.replace(".wav", "_442_dr.wav"))
e_file = os.path.join(base_dir, vocal_file.replace(".wav", "_442_dr_v2.wav"))
v_file = os.path.join(cur_dir, "vocal.wav")
a_file = os.path.join(cur_dir, "acc.wav")
cur_id = cur_dir.split("/")[-1]
err = s_inst.after_process(cur_id, cur_dir, i_file, e_file, v_file, a_file, True, False)
print("err={}, sp={}".format(err, time.time() - sstime))
def get_metop500():
arr = [
"611752105030249067",
"611752105030248972",
"611752105030249414",
"611752105030249374",
"611752105030249030",
"611752105030249127",
"611752105030249091",
"611752105030249233",
"611752105030249036",
"611752105030249281",
"611752105030249040",
"611752105030249052",
"611752105030249394",
"611752105030249347",
"611752105030249342",
"611752105030249282",
"611752105030249292",
"611752105030249356",
"611752105030249302",
"611752105030249377",
"611752105030248973",
"611752105030249393",
"611752105030249398",
"611752105030250695",
"611752105030249213",
"611752105030250739",
"611752105030249206",
"611752105030249074",
"611752105030249387",
"611752105030250702",
"611752105030249365",
"611752105030249011",
"611752105030249319",
"611752105030249016",
"611752105030249176",
"611752105030250690",
"611752105030250691",
"611752105030249032",
"611752105030249370",
"611752105030249410",
"611752105030249355",
"611752105030250730",
"611752105030249022",
"611752105030249240",
"611752105030249296",
"611752105030249070",
"611752105030249322",
"611752105030249402",
"611752105030249386",
"611752105030249280",
"611752105030249038",
"611752105030250743",
"611752105030249136",
"611752105030249034",
"611752105030249403",
"611752105030249104",
"611752105030249105",
"611752105030249359",
"611752105030250728",
"611752105030249338",
"611752105030249216",
"611752105030249334",
"611752105030249037",
"611752105030249264",
"611752105030249284",
"611752105030249267",
"611752105030249010",
"611752105030249431",
"611752105030249364",
"611752105030249243",
"611752105030249397",
"611752105030249041",
"611752105030249118",
"611752105030249283",
"611752105030249340",
"611752105030249250",
"611752105030249048",
"611752105030249336",
"611752105030249371",
"611752105030249372",
"611752105030249273",
"611752105030249366",
"611752105030249352",
"611752105030249049",
"611752105030249278",
"611752105030249401",
"611752105030249258",
"611752105030249160",
"611752105030249348",
"611752105030249071",
"611752105030249175",
"611752105030249053",
"611752105030249035",
"611752105030249375",
"611752105030249417",
"611752105030249055",
"611752105030249275",
"611752105030249177",
"611752105028480653",
"611752105030249385",
"611752105030249406",
"611752105030249383",
"611752105030249295",
"611752105030250699",
"611752105030249289",
"611752105030248965",
"611752105030249128",
"611752105030249173",
"611752105030249019",
"611752105030249333",
"611752105030249361",
"611752105030250733",
"611752105030249112",
"611752105030249293",
"611752105030249391",
"611752105030249195",
"611752105030249324",
"611752105030249388",
"611752105030249134",
"611752105030249073",
"611752105030249174",
"611752105030249353",
"611752105030249287",
"611752105030249113",
"611752105030249227"
]
all = [
"611752105026649069",
"611752105027201163",
"611752105027601574",
"611752105027602999",
"611752105028392007",
"611752105028480056",
"611752105028480075",
"611752105028480653",
"611752105029330944",
"611752105029790637",
"611752105029951597",
"611752105029951604",
"611752105029951624",
"611752105029956352",
"611752105030248965",
"611752105030248971",
"611752105030248972",
"611752105030248973",
"611752105030248974",
"611752105030248975",
"611752105030248976",
"611752105030248977",
"611752105030248978",
"611752105030248979",
"611752105030248980",
"611752105030248981",
"611752105030248982",
"611752105030248983",
"611752105030248985",
"611752105030248986",
"611752105030248987",
"611752105030248988",
"611752105030248989",
"611752105030248990",
"611752105030248991",
"611752105030248992",
"611752105030248993",
"611752105030248994",
"611752105030248995",
"611752105030248996",
"611752105030248997",
"611752105030248998",
"611752105030248999",
"611752105030249000",
"611752105030249001",
"611752105030249002",
"611752105030249003",
"611752105030249004",
"611752105030249005",
"611752105030249006",
"611752105030249007",
"611752105030249008",
"611752105030249009",
"611752105030249010",
"611752105030249011",
"611752105030249012",
"611752105030249013",
"611752105030249014",
"611752105030249015",
"611752105030249016",
"611752105030249017",
"611752105030249018",
"611752105030249019",
"611752105030249020",
"611752105030249021",
"611752105030249022",
"611752105030249023",
"611752105030249024",
"611752105030249025",
"611752105030249026",
"611752105030249027",
"611752105030249028",
"611752105030249029",
"611752105030249030",
"611752105030249031",
"611752105030249032",
"611752105030249033",
"611752105030249034",
"611752105030249035",
"611752105030249036",
"611752105030249037",
"611752105030249038",
"611752105030249039",
"611752105030249040",
"611752105030249041",
"611752105030249042",
"611752105030249043",
"611752105030249044",
"611752105030249045",
"611752105030249046",
"611752105030249047",
"611752105030249048",
"611752105030249049",
"611752105030249050",
"611752105030249051",
"611752105030249052",
"611752105030249053",
"611752105030249054",
"611752105030249055",
"611752105030249056",
"611752105030249057",
"611752105030249058",
"611752105030249059",
"611752105030249060",
"611752105030249062",
"611752105030249063",
"611752105030249064",
"611752105030249065",
"611752105030249067",
"611752105030249068",
"611752105030249070",
"611752105030249071",
"611752105030249072",
"611752105030249073",
"611752105030249074",
"611752105030249075",
"611752105030249076",
"611752105030249077",
"611752105030249078",
"611752105030249079",
"611752105030249080",
"611752105030249081",
"611752105030249082",
"611752105030249083",
"611752105030249084",
"611752105030249085",
"611752105030249086",
"611752105030249087",
"611752105030249088",
"611752105030249089",
"611752105030249090",
"611752105030249091",
"611752105030249092",
"611752105030249093",
"611752105030249094",
"611752105030249095",
"611752105030249096",
"611752105030249098",
"611752105030249099",
"611752105030249100",
"611752105030249101",
"611752105030249102",
"611752105030249103",
"611752105030249104",
"611752105030249105",
"611752105030249106",
"611752105030249107",
"611752105030249108",
"611752105030249109",
"611752105030249110",
"611752105030249111",
"611752105030249112",
"611752105030249113",
"611752105030249114",
"611752105030249115",
"611752105030249116",
"611752105030249117",
"611752105030249118",
"611752105030249119",
"611752105030249120",
"611752105030249121",
"611752105030249122",
"611752105030249123",
"611752105030249124",
"611752105030249125",
"611752105030249126",
"611752105030249127",
"611752105030249128",
"611752105030249129",
"611752105030249130",
"611752105030249131",
"611752105030249132",
"611752105030249133",
"611752105030249134",
"611752105030249135",
"611752105030249136",
"611752105030249137",
"611752105030249138",
"611752105030249139",
"611752105030249140",
"611752105030249141",
"611752105030249142",
"611752105030249143",
"611752105030249144",
"611752105030249145",
"611752105030249146",
"611752105030249147",
"611752105030249148",
"611752105030249150",
"611752105030249151",
"611752105030249152",
"611752105030249153",
"611752105030249154",
"611752105030249155",
"611752105030249157",
"611752105030249158",
"611752105030249159",
"611752105030249160",
"611752105030249161",
"611752105030249162",
"611752105030249163",
"611752105030249165",
"611752105030249166",
"611752105030249167",
"611752105030249168",
"611752105030249170",
"611752105030249171",
"611752105030249172",
"611752105030249173",
"611752105030249174",
"611752105030249175",
"611752105030249176",
"611752105030249177",
"611752105030249178",
"611752105030249179",
"611752105030249180",
"611752105030249181",
"611752105030249182",
"611752105030249183",
"611752105030249185",
"611752105030249186",
"611752105030249187",
"611752105030249188",
"611752105030249189",
"611752105030249190",
"611752105030249191",
"611752105030249192",
"611752105030249193",
"611752105030249194",
"611752105030249195",
"611752105030249196",
"611752105030249197",
"611752105030249198",
"611752105030249199",
"611752105030249200",
"611752105030249201",
"611752105030249202",
"611752105030249203",
"611752105030249204",
"611752105030249205",
"611752105030249206",
"611752105030249207",
"611752105030249208",
"611752105030249209",
"611752105030249210",
"611752105030249211",
"611752105030249212",
"611752105030249213",
"611752105030249214",
"611752105030249216",
"611752105030249217",
"611752105030249218",
"611752105030249219",
"611752105030249220",
"611752105030249221",
"611752105030249223",
"611752105030249224",
"611752105030249225",
"611752105030249226",
"611752105030249227",
"611752105030249228",
"611752105030249229",
"611752105030249230",
"611752105030249231",
"611752105030249232",
"611752105030249233",
"611752105030249234",
"611752105030249235",
"611752105030249236",
"611752105030249237",
"611752105030249238",
"611752105030249239",
"611752105030249240",
"611752105030249241",
"611752105030249242",
"611752105030249243",
"611752105030249244",
"611752105030249245",
"611752105030249247",
"611752105030249248",
"611752105030249249",
"611752105030249250",
"611752105030249251",
"611752105030249252",
"611752105030249253",
"611752105030249255",
"611752105030249256",
"611752105030249257",
"611752105030249258",
"611752105030249259",
"611752105030249260",
"611752105030249261",
"611752105030249262",
"611752105030249264",
"611752105030249265",
"611752105030249266",
"611752105030249267",
"611752105030249269",
"611752105030249270",
"611752105030249271",
"611752105030249273",
"611752105030249274",
"611752105030249275",
"611752105030249277",
"611752105030249278",
"611752105030249279",
"611752105030249280",
"611752105030249281",
"611752105030249282",
"611752105030249283",
"611752105030249284",
"611752105030249287",
"611752105030249288",
"611752105030249289",
"611752105030249290",
"611752105030249292",
"611752105030249293",
"611752105030249294",
"611752105030249295",
"611752105030249296",
"611752105030249297",
"611752105030249298",
"611752105030249299",
"611752105030249300",
"611752105030249301",
"611752105030249302",
"611752105030249303",
"611752105030249307",
"611752105030249308",
"611752105030249309",
"611752105030249310",
"611752105030249313",
"611752105030249314",
"611752105030249315",
"611752105030249316",
"611752105030249317",
"611752105030249318",
"611752105030249319",
"611752105030249320",
"611752105030249321",
"611752105030249322",
"611752105030249323",
"611752105030249324",
"611752105030249325",
"611752105030249327",
"611752105030249328",
"611752105030249329",
"611752105030249330",
"611752105030249331",
"611752105030249332",
"611752105030249333",
"611752105030249334",
"611752105030249336",
"611752105030249337",
"611752105030249338",
"611752105030249339",
"611752105030249340",
"611752105030249341",
"611752105030249342",
"611752105030249343",
"611752105030249344",
"611752105030249345",
"611752105030249346",
"611752105030249347",
"611752105030249348",
"611752105030249349",
"611752105030249350",
"611752105030249351",
"611752105030249352",
"611752105030249353",
"611752105030249354",
"611752105030249355",
"611752105030249356",
"611752105030249357",
"611752105030249358",
"611752105030249359",
"611752105030249360",
"611752105030249361",
"611752105030249362",
"611752105030249363",
"611752105030249364",
"611752105030249365",
"611752105030249366",
"611752105030249367",
"611752105030249368",
"611752105030249369",
"611752105030249370",
"611752105030249371",
"611752105030249372",
"611752105030249373",
"611752105030249374",
"611752105030249375",
"611752105030249376",
"611752105030249377",
"611752105030249378",
"611752105030249379",
"611752105030249380",
"611752105030249381",
"611752105030249383",
"611752105030249384",
"611752105030249385",
"611752105030249386",
"611752105030249387",
"611752105030249388",
"611752105030249389",
"611752105030249390",
"611752105030249391",
"611752105030249392",
"611752105030249393",
"611752105030249394",
"611752105030249395",
"611752105030249396",
"611752105030249397",
"611752105030249398",
"611752105030249399",
"611752105030249401",
"611752105030249402",
"611752105030249403",
"611752105030249404",
"611752105030249405",
"611752105030249406",
"611752105030249407",
"611752105030249408",
"611752105030249409",
"611752105030249410",
"611752105030249412",
"611752105030249413",
"611752105030249414",
"611752105030249415",
"611752105030249416",
"611752105030249417",
"611752105030249418",
"611752105030249419",
"611752105030249420",
"611752105030249421",
"611752105030249431",
"611752105030249624",
"611752105030250688",
"611752105030250689",
"611752105030250690",
"611752105030250691",
"611752105030250692",
"611752105030250693",
"611752105030250695",
"611752105030250697",
"611752105030250698",
"611752105030250699",
"611752105030250700",
"611752105030250701",
"611752105030250702",
"611752105030250704",
"611752105030250707",
"611752105030250711",
"611752105030250712",
"611752105030250713",
"611752105030250714",
"611752105030250715",
"611752105030250716",
"611752105030250717",
"611752105030250718",
"611752105030250719",
"611752105030250720",
"611752105030250721",
"611752105030250723",
"611752105030250725",
"611752105030250726",
"611752105030250728",
"611752105030250729",
"611752105030250730",
"611752105030250731",
"611752105030250732",
"611752105030250733",
"611752105030250735",
"611752105030250736",
"611752105030250738",
"611752105030250739",
"611752105030250740",
"611752105030250741",
"611752105030250742",
"611752105030250743"
]
new_arr = []
for sid in all:
if sid in arr:
continue
new_arr.append(sid)
print("len={}".format(len(new_arr)))
return new_arr
def get_me_3_w4_zy():
arr = [
"611752105015523266",
"611752105016527562",
"611752105017233541",
"611752105019423720",
"611752105030113709",
"611752105030414513",
"611752105030414549",
"611752105030414557",
"611752105030414568",
"611752105030414576",
"611752105030414580",
"611752105030414584",
"611752105030414588",
"611752105030414590",
"611752105030414597",
"611752105030414600",
"611752105030414608",
"611752105030414613",
"611752105030414615",
"611752105030414619",
"611752105030414633",
"611752105030414638",
"611752105030414644",
"611752105030414647",
"611752105030414655",
"611752105030414660",
"611752105030414663",
"611752105030414669",
"611752105030414674",
"611752105030414678",
"611752105030414680",
"611752105030414682",
"611752105030414686",
"611752105030414689",
"611752105030414696",
"611752105030414702",
"611752105030414706",
"611752105030414707",
"611752105030414711",
"611752105030414717",
"611752105030414729",
"611752105030414742",
"611752105030414752",
"611752105030414757",
"611752105030414761",
"611752105030414763",
"611752105030414766",
"611752105030414773",
"611752105030414776",
"611752105030414777",
"611752105030414779",
"611752105030414784",
"611752105030414890",
"611752105030414907",
"611752105030414915",
"611752105030414919",
"611752105030414925",
"611752105030414929",
"611752105030414932",
"611752105030414935",
"611752105030414937",
"611752105030414943",
"611752105030414948",
"611752105030414949",
"611752105030414957",
"611752105030414962",
"611752105030414963",
"611752105030414968",
"611752105030414973",
"611752105030414976",
"611752105030414981",
"611752105030414986",
"611752105030414988",
"611752105030414990",
"611752105030414993",
"611752105030414995",
"611752105030415003",
"611752105030415007",
"611752105030415009",
"611752105030415014",
"611752105030415018",
"611752105030415032",
"611752105030415044",
"611752105030415050",
"611752105030415052",
"611752105030415056",
"611752105030415058",
"611752105030415062",
"611752105030415067",
"611752105030415071",
"611752105030415074",
"611752105030415078",
"611752105030415083",
"611752105030415087",
"611752105030415094",
"611752105030415100",
"611752105030415103",
"611752105030425986",
"611752105030426004"
]
return arr
def generate_arr():
# arr = [
# "611752105020256284",
# "611752105020282612",
# "611752105020282613",
# "611752105020286433",
# "611752105020286443",
# "611752105020286446",
# "611752105020286501",
# "611752105020290639",
# "611752105020290695",
# "611752105020315328",
# "611752105020315368",
# "611752105020325137",
# "611752105020336946",
# "611752105020336950",
# "611752105020343687",
# "611752105020343699",
# "611752105020350988",
# "611752105020350990",
# "611752105020351134",
# "611752105020357112",
# "611752105020376320",
# "611752105020378620",
# "611752105020382559",
# "611752105020387015",
# "611752105020390950",
# "611752105020394121",
# "611752105020394297",
# "611752105020411654",
# "611752105020417488",
# "611752105020417688",
# "611752105020548211",
# "611752105020563523",
# "611752105021273980",
# "611752105021285282",
# "611752105021330812",
# "611752105021332759",
# "611752105021375100",
# "611752105021442406",
# "611752105021442417",
# "611752105021453011",
# "611752105022345104",
# "611752105022389596",
# "611752105022446809",
# "611752105022647082",
# "611752105022667231",
# "611752105022735101",
# "611752105022736204",
# "611752105022745595",
# "611752105022770952",
# "611752105022842004",
# "611752105022842477",
# "611752105023434557",
# "611752105023532439",
# "611752105023623965",
# "611752105023811083",
# "611752105024250202",
# "611752105024429936",
# "611752105024628047",
# "611752105024676794",
# "611752105024678976",
# "611752105024679221",
# "611752105024714646",
# "611752105024786030",
# "611752105024953316",
# "611752105025104181",
# "611752105025231610",
# "611752105025510149",
# "611752105026189342",
# "611752105026523547",
# "611752105026707760",
# "611752105026771723",
# "611752105026946178",
# "611752105027047993",
# "611752105027188746",
# "611752105027189453",
# "611752105027302268",
# "611752105027557408",
# "611752105027588072",
# "611752105028650636",
# "611752105028683824",
# "611752105029689090",
# "611752105029954089",
# "611752105029954168",
# "611752105029955214",
# "611752105029990849",
# "611752105029993297",
# "611752105030047424",
# "611752105030077711",
# "611752105030104548",
# "611752105030419624",
# "611752105030419633",
# "611752105030419688",
# "611752105030433779"
# ]
# arr = get_metop500()
arr = get_me_3_w4_zy()
s_inst = SongCoverInference()
for sid in arr:
sstime = time.time()
dir = os.path.join("/data/rsync/jianli.yang/AutoCoverTool/data/inf_users/me_3_w4_zy", sid)
# dir = os.path.join("/data/rsync/jianli.yang/AutoCoverTool/data/inf_users/me_top500", sid)
err = s_inst.process_one(sid, dir, True)
print("sid={}, err={}, sp={}".format(sid, err, time.time() - sstime))
def test_rate():
arr = [
"611752105020256284",
"611752105020286433",
"611752105020286443",
"611752105020286446",
"611752105020290639",
"611752105020290695",
"611752105020315328",
"611752105020315368",
"611752105020336950",
"611752105020343687",
"611752105020343699",
"611752105020351134",
"611752105020357112",
"611752105020378620",
"611752105020387015",
"611752105020394121",
"611752105020394297",
"611752105020411654",
"611752105020417688",
"611752105020548211",
"611752105020563523",
"611752105021285282",
"611752105021332759",
"611752105022446809",
"611752105022647082",
"611752105022667231",
"611752105022735101",
"611752105022736204",
"611752105022745595",
"611752105022770952",
"611752105022842004",
"611752105022842477",
"611752105023434557",
"611752105023532439",
"611752105023623965",
"611752105024250202",
"611752105024628047",
"611752105024676794",
"611752105024678976",
"611752105024679221",
"611752105024953316",
"611752105025104181",
"611752105026189342",
"611752105026523547",
"611752105026707760",
"611752105026771723",
"611752105026946178",
"611752105027047993",
"611752105027188746",
"611752105027189453",
"611752105027302268",
"611752105027557408",
"611752105028650636",
"611752105028683824",
"611752105029990849",
"611752105029993297",
"611752105030077711",
"611752105030104548",
"611752105030419624",
"611752105030419633",
"611752105030419688",
"611752105030433779"
]
s_inst = SongCoverInference()
for sid in arr:
vocal_path = "data/inf_users/me_3_w4/{}/cache/vocal.wav".format(sid)
tm = s_inst.get_start_ms(vocal_path)
print("res,{},{}".format(vocal_path, tm))
def test():
arr = [
# "611752105020343687",
# "611752105023532439",
"611752105030419688",
]
base_dir = "/data/rsync/jianli.yang/AutoCoverTool/data/test"
s_inst = SongCoverInference()
for cid in arr:
st = time.time()
err = s_inst.process_one(cid, os.path.join(base_dir, cid), False)
print("cid={} RealFinish err={} sp={}".format(cid, err, time.time() - st))
if __name__ == '__main__':
- # test()
+ test()
# test_rate()
- test_volume_dir()
+ # test_volume_dir()
# generate_arr()
# test_volume_dir()
# s_inst = SongCoverInference()
# sstime = time.time()
# err = s_inst.process_one("611752105030249038",
# "/data/rsync/jianli.yang/AutoCoverTool/data/inf_users/me_top500/611752105030249038", False)
# # i_file = "/data/rsync/jianli.yang/AutoCoverTool/data/out_data/me_top500/611752105030249121/611752105030249121_5629499489839033.wav"
# # e_file = "/data/rsync/jianli.yang/AutoCoverTool/data/out_data/me_top500/611752105030249121/611752105030249121_5629499489839033.wav"
# # v_file = "/data/rsync/jianli.yang/AutoCoverTool/data/inf_users/me_top500/611752105030249121/vocal.wav"
# # a_file = "/data/rsync/jianli.yang/AutoCoverTool/data/inf_users/me_top500/611752105030249121/acc.wav"
# # w_dir = "/data/rsync/jianli.yang/AutoCoverTool/data/inf_users/me_top500/611752105030249121"
# #
# # err = s_inst.after_process("611752105030248965", w_dir, i_file, e_file, v_file, a_file)
# print("err={}, sp={}".format(err, time.time() - sstime))
diff --git a/AutoCoverTool/script/test_simple_mix.py b/AutoCoverTool/script/test_simple_mix.py
new file mode 100644
index 0000000..b4309df
--- /dev/null
+++ b/AutoCoverTool/script/test_simple_mix.py
@@ -0,0 +1,67 @@
+"""
+将人声和伴奏合并起来
+1. 人声重采样到44k
+2.
+"""
+import os
+import time
+
+gs_draw_volume = "/Users/yangjianli/linux/opt/soft/bin/draw_volume"
+gs_simple_mixer = "/Users/yangjianli/linux/opt/soft/bin/simple_mixer"
+gs_ffmpeg = "/usr/local/bin/ffmpeg"
+
+
+def process(dir):
+ """
+ 文件夹下要求:
+ 1. effect.wav
+ 2. vocal.wav
+ 3. acc.wav
+ 中间结果: effect_442.wav, effect_442_dv.wav
+ 最终输出: mix.wav
+ :param dir:
+ :return:
+ """
+ st = time.time()
+ effect_wav = os.path.join(dir, "effect.wav")
+ effect442_wav = os.path.join(dir, "effect_442.wav")
+ effect442dv_wav = os.path.join(dir, "effect_442_dv.wav")
+ mix_wav = os.path.join(dir, "mix.wav")
+ vocal_wav = os.path.join(dir, "vocal.wav")
+ acc_wav = os.path.join(dir, "acc.wav")
+ if not os.path.exists(effect_wav):
+ print("no {}".format(effect_wav))
+ return -1
+ if not os.path.exists(vocal_wav):
+ print("no {}".format(vocal_wav))
+ return -1
+ if not os.path.exists(acc_wav):
+ print("no {}".format(acc_wav))
+ return -1
+ # 转码到44k双声道
+ cmd = "{} -i {} -ar 44100 -ac 2 -y {}".format(gs_ffmpeg, effect_wav, effect442_wav)
+ os.system(cmd)
+ if not os.path.exists(effect442_wav):
+ print("err! {}".format(cmd))
+ return -2
+
+ # 拉伸
+ cmd = "{} {} {} {}".format(gs_draw_volume, effect442_wav, vocal_wav, effect442dv_wav)
+ os.system(cmd)
+ if not os.path.exists(effect442dv_wav):
+ print("err! {}".format(cmd))
+ return -1
+
+ # 合并
+ cmd = "{} {} {} {}".format(gs_simple_mixer, effect442dv_wav, acc_wav, mix_wav)
+ os.system(cmd)
+ if not os.path.exists(mix_wav):
+ print("err! {}".format(cmd))
+ return -1
+ print("{} success! sp={}".format(dir, time.time() - st))
+ return 0
+
+
+if __name__ == '__main__':
+ process(
+ "/Users/yangjianli/starmaker-work/research/tmp_code/SVC方案调研/prod/out_0327/test/me_3_w4_10_compare_v3_src/611752105020336950")

File Metadata

Mime Type
text/x-diff
Expires
Sun, Jan 12, 08:29 (1 d, 11 h)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
1347142
Default Alt Text
(60 KB)

Event Timeline