ffmpeg：无声删除部分：有效删除视频的几个部分

Question

我正在尝试删除没有（或很少）音频的视频部分。为此，我使用了 audacity ( Analyze->Sound finder ) 并导出了Label Track。这会导致如下结果：

0.000000    5.170000    1
12.520000   12.630000   2
14.400000   15.660000   3
17.430000   22.150000   4
...

使用这个正则表达式：([\d]+.[\d]{6})\t([\d]+.[\d]{6})\t([\d]+)\n>ffmpeg -i VL1.mp4 -strict -2 -ss \1 -to \2 buff.mp4\nffmpeg -f concat -i <(echo "file '/home/rene/videotest/output.mp4'\nfile '/home/rene/videotest/buff.mp4'") -c copy output2.mp4\nrm buff.mp4\nmv output2.mp4 output.mp4\n和一些手动编辑，我得到了这个：

#!/bin/bash

ffmpeg -i VL1.mp4 -strict -2 -ss 0.000000 -to 5.170000 output.mp4
ffmpeg -i VL1.mp4 -strict -2 -ss 12.520000 -to 12.630000 buff.mp4
ffmpeg -f concat -i <(echo "file '/home/rene/videotest/output.mp4'
file '/home/rene/videotest/buff.mp4'") -c copy output2.mp4
rm buff.mp4
mv output2.mp4 output.mp4
ffmpeg -i VL1.mp4 -strict -2 -ss 14.400000 -to 15.660000 buff.mp4
ffmpeg -f concat -i <(echo "file '/home/rene/videotest/output.mp4'
file '/home/rene/videotest/buff.mp4'") -c copy output2.mp4
rm buff.mp4
mv output2.mp4 output.mp4
ffmpeg -i VL1.mp4 -strict -2 -ss 17.430000 -to 22.150000 buff.mp4
ffmpeg -f concat -i <(echo "file '/home/rene/videotest/output.mp4'
file '/home/rene/videotest/buff.mp4'") -c copy output2.mp4
rm buff.mp4
mv output2.mp4 output.mp4
...

这工作得很好，我得到一个output.mp4只包含我想要的部分的文件。

不幸的是，这非常慢 - 我担心它会破坏我的硬盘（因为每个部分都buff.mp4创建了一个文件，一个包含所有现有部分的新文件加上这个短片被写入硬盘，包含现有部分的旧文件被删除）。由于大多数剪辑真的很短（通常不到几秒），我的想法是不将文件写入buff.mp4硬盘，而是通过将其传递给 ffmpeg <（因此将其保存在 RAM 中？）。第二件事是追加output.mp4而不是每次都重写文件。

不幸的是，我对 ffmpeg 和 bash 的总体了解太少了。有人可以帮我吗？

我应该能够在没有手动正则表达式的情况下编写一个不错的脚本。当然，我会在之后发布这个。

Answer 1

https://github.com/carykh/jumpcutter（MIT许可证）会自动删除视频中没有或很少音频的部分。它依赖于 ffmpeg，管道是用 Python 3 编码的（在 Ubuntu、Microsoft Windows 和可能的 Mac OS X 上运行）。

说明：https://www.youtube.com/watch?v =DQ8orIurGxw

脚本（MIT许可，作者：carykh）：

from contextlib import closing
from PIL import Image
import subprocess
from audiotsm import phasevocoder
from audiotsm.io.wav import WavReader, WavWriter
from scipy.io import wavfile
import numpy as np
import re
import math
from shutil import copyfile, rmtree
import os
import argparse
from pytube import YouTube

def downloadFile(url):
    name = YouTube(url).streams.first().download()
    newname = name.replace(' ','_')
    os.rename(name,newname)
    return newname

def getMaxVolume(s):
    maxv = float(np.max(s))
    minv = float(np.min(s))
    return max(maxv,-minv)

def copyFrame(inputFrame,outputFrame):
    src = TEMP_FOLDER+"/frame{:06d}".format(inputFrame+1)+".jpg"
    dst = TEMP_FOLDER+"/newFrame{:06d}".format(outputFrame+1)+".jpg"
    if not os.path.isfile(src):
        return False
    copyfile(src, dst)
    if outputFrame%20 == 19:
        print(str(outputFrame+1)+" time-altered frames saved.")
    return True

def inputToOutputFilename(filename):
    dotIndex = filename.rfind(".")
    return filename[:dotIndex]+"_ALTERED"+filename[dotIndex:]

def createPath(s):
    #assert (not os.path.exists(s)), "The filepath "+s+" already exists. Don't want to overwrite it. Aborting."

    try:  
        os.mkdir(s)
    except OSError:  
        assert False, "Creation of the directory %s failed. (The TEMP folder may already exist. Delete or rename it, and try again.)"

def deletePath(s): # Dangerous! Watch out!
    try:  
        rmtree(s,ignore_errors=False)
    except OSError:  
        print ("Deletion of the directory %s failed" % s)
        print(OSError)

parser = argparse.ArgumentParser(description='Modifies a video file to play at different speeds when there is sound vs. silence.')
parser.add_argument('--input_file', type=str,  help='the video file you want modified')
parser.add_argument('--url', type=str, help='A youtube url to download and process')
parser.add_argument('--output_file', type=str, default="", help="the output file. (optional. if not included, it'll just modify the input file name)")
parser.add_argument('--silent_threshold', type=float, default=0.03, help="the volume amount that frames' audio needs to surpass to be consider \"sounded\". It ranges from 0 (silence) to 1 (max volume)")
parser.add_argument('--sounded_speed', type=float, default=1.00, help="the speed that sounded (spoken) frames should be played at. Typically 1.")
parser.add_argument('--silent_speed', type=float, default=5.00, help="the speed that silent frames should be played at. 999999 for jumpcutting.")
parser.add_argument('--frame_margin', type=float, default=1, help="some silent frames adjacent to sounded frames are included to provide context. How many frames on either the side of speech should be included? That's this variable.")
parser.add_argument('--sample_rate', type=float, default=44100, help="sample rate of the input and output videos")
parser.add_argument('--frame_rate', type=float, default=30, help="frame rate of the input and output videos. optional... I try to find it out myself, but it doesn't always work.")
parser.add_argument('--frame_quality', type=int, default=3, help="quality of frames to be extracted from input video. 1 is highest, 31 is lowest, 3 is the default.")

args = parser.parse_args()



frameRate = args.frame_rate
SAMPLE_RATE = args.sample_rate
SILENT_THRESHOLD = args.silent_threshold
FRAME_SPREADAGE = args.frame_margin
NEW_SPEED = [args.silent_speed, args.sounded_speed]
if args.url != None:
    INPUT_FILE = downloadFile(args.url)
else:
    INPUT_FILE = args.input_file
URL = args.url
FRAME_QUALITY = args.frame_quality

assert INPUT_FILE != None , "why u put no input file, that dum"

if len(args.output_file) >= 1:
    OUTPUT_FILE = args.output_file
else:
    OUTPUT_FILE = inputToOutputFilename(INPUT_FILE)

TEMP_FOLDER = "TEMP"
AUDIO_FADE_ENVELOPE_SIZE = 400 # smooth out transitiion's audio by quickly fading in/out (arbitrary magic number whatever)

createPath(TEMP_FOLDER)

command = "ffmpeg -i "+INPUT_FILE+" -qscale:v "+str(FRAME_QUALITY)+" "+TEMP_FOLDER+"/frame%06d.jpg -hide_banner"
subprocess.call(command, shell=True)

command = "ffmpeg -i "+INPUT_FILE+" -ab 160k -ac 2 -ar "+str(SAMPLE_RATE)+" -vn "+TEMP_FOLDER+"/audio.wav"

subprocess.call(command, shell=True)

command = "ffmpeg -i "+TEMP_FOLDER+"/input.mp4 2>&1"
f = open(TEMP_FOLDER+"/params.txt", "w")
subprocess.call(command, shell=True, stdout=f)



sampleRate, audioData = wavfile.read(TEMP_FOLDER+"/audio.wav")
audioSampleCount = audioData.shape[0]
maxAudioVolume = getMaxVolume(audioData)

f = open(TEMP_FOLDER+"/params.txt", 'r+')
pre_params = f.read()
f.close()
params = pre_params.split('\n')
for line in params:
    m = re.search('Stream #.*Video.* ([0-9]*) fps',line)
    if m is not None:
        frameRate = float(m.group(1))

samplesPerFrame = sampleRate/frameRate

audioFrameCount = int(math.ceil(audioSampleCount/samplesPerFrame))

hasLoudAudio = np.zeros((audioFrameCount))



for i in range(audioFrameCount):
    start = int(i*samplesPerFrame)
    end = min(int((i+1)*samplesPerFrame),audioSampleCount)
    audiochunks = audioData[start:end]
    maxchunksVolume = float(getMaxVolume(audiochunks))/maxAudioVolume
    if maxchunksVolume >= SILENT_THRESHOLD:
        hasLoudAudio[i] = 1

chunks = [[0,0,0]]
shouldIncludeFrame = np.zeros((audioFrameCount))
for i in range(audioFrameCount):
    start = int(max(0,i-FRAME_SPREADAGE))
    end = int(min(audioFrameCount,i+1+FRAME_SPREADAGE))
    shouldIncludeFrame[i] = np.max(hasLoudAudio[start:end])
    if (i >= 1 and shouldIncludeFrame[i] != shouldIncludeFrame[i-1]): # Did we flip?
        chunks.append([chunks[-1][1],i,shouldIncludeFrame[i-1]])

chunks.append([chunks[-1][1],audioFrameCount,shouldIncludeFrame[i-1]])
chunks = chunks[1:]

outputAudioData = np.zeros((0,audioData.shape[1]))
outputPointer = 0

lastExistingFrame = None
for chunk in chunks:
    audioChunk = audioData[int(chunk[0]*samplesPerFrame):int(chunk[1]*samplesPerFrame)]

    sFile = TEMP_FOLDER+"/tempStart.wav"
    eFile = TEMP_FOLDER+"/tempEnd.wav"
    wavfile.write(sFile,SAMPLE_RATE,audioChunk)
    with WavReader(sFile) as reader:
        with WavWriter(eFile, reader.channels, reader.samplerate) as writer:
            tsm = phasevocoder(reader.channels, speed=NEW_SPEED[int(chunk[2])])
            tsm.run(reader, writer)
    _, alteredAudioData = wavfile.read(eFile)
    leng = alteredAudioData.shape[0]
    endPointer = outputPointer+leng
    outputAudioData = np.concatenate((outputAudioData,alteredAudioData/maxAudioVolume))

    #outputAudioData[outputPointer:endPointer] = alteredAudioData/maxAudioVolume

    # smooth out transitiion's audio by quickly fading in/out

    if leng < AUDIO_FADE_ENVELOPE_SIZE:
        outputAudioData[outputPointer:endPointer] = 0 # audio is less than 0.01 sec, let's just remove it.
    else:
        premask = np.arange(AUDIO_FADE_ENVELOPE_SIZE)/AUDIO_FADE_ENVELOPE_SIZE
        mask = np.repeat(premask[:, np.newaxis],2,axis=1) # make the fade-envelope mask stereo
        outputAudioData[outputPointer:outputPointer+AUDIO_FADE_ENVELOPE_SIZE] *= mask
        outputAudioData[endPointer-AUDIO_FADE_ENVELOPE_SIZE:endPointer] *= 1-mask

    startOutputFrame = int(math.ceil(outputPointer/samplesPerFrame))
    endOutputFrame = int(math.ceil(endPointer/samplesPerFrame))
    for outputFrame in range(startOutputFrame, endOutputFrame):
        inputFrame = int(chunk[0]+NEW_SPEED[int(chunk[2])]*(outputFrame-startOutputFrame))
        didItWork = copyFrame(inputFrame,outputFrame)
        if didItWork:
            lastExistingFrame = inputFrame
        else:
            copyFrame(lastExistingFrame,outputFrame)

    outputPointer = endPointer

wavfile.write(TEMP_FOLDER+"/audioNew.wav",SAMPLE_RATE,outputAudioData)

'''
outputFrame = math.ceil(outputPointer/samplesPerFrame)
for endGap in range(outputFrame,audioFrameCount):
    copyFrame(int(audioSampleCount/samplesPerFrame)-1,endGap)
'''

command = "ffmpeg -framerate "+str(frameRate)+" -i "+TEMP_FOLDER+"/newFrame%06d.jpg -i "+TEMP_FOLDER+"/audioNew.wav -strict -2 "+OUTPUT_FILE
subprocess.call(command, shell=True)

deletePath(TEMP_FOLDER)

Answer 2

扩展弗兰克的答案，有更好的 Jumpcutter 替代品：

https://github.com/carykh/jumpcutter/issues/180

编辑：不幸的是，这个问题已在 Github 上删除，但您可以从 Web Archive 中看到它：https: //web.archive.org/web/20201203163529/https ://github.com/carykh/jumpcutter/issues/180

使用自动编辑器：

https://github.com/WyattBlue/auto-editor