An update to my automated silence trimming script

Follow me on YouTube and Twitter for more video editing tricks with ffmpeg and a little python now!

I recently updated my python script for automatically removing the silence parts of a video.

Previously, I had to call the shell script separate to generate the silence timestamps.

Now, the python script grabs the output of the shell script directly using subprocess run.

Script

#!/usr/bin/env python

import sys
import subprocess
import os
from moviepy.editor import VideoFileClip, concatenate_videoclips

input_path = sys.argv[1]
out_path = sys.argv[2]
threshold = sys.argv[3]
duration = sys.argv[4]

try:
    ease = float(sys.argv[5])
except IndexError:
    ease = 0.2

minimum_duration = 1.0

def generate_timestamps(path, threshold, duration):
    command = "detect_silence {} {} {}".format(input_path, threshold, duration)
    output = subprocess.run(command, shell=True, capture_output=True, text=True)
    return output.stdout.split('\n')[:-1]


def main():
    count = 0
    last = 0
    timestamps = generate_timestamps(input_path, threshold, duration)
    print("Timestamps: {}".format(timestamps))
    video = VideoFileClip(input_path)
    full_duration = video.duration
    clips = []

    for times in timestamps:
        end,dur = times.strip().split()
        print("End: {}, Duration: {}".format(end, dur))

        to = float(end) - float(dur) + ease

        start = float(last)
        clip_duration = float(to) - start
        # Clips less than one seconds don't seem to work
        print("Clip Duration: {} seconds".format(clip_duration))

        if clip_duration < minimum_duration:
            continue

        if full_duration - to < minimum_duration:
            continue


        print("Clip {} (Start: {}, End: {})".format(count, start, to))
        clip = video.subclip(start, to)
        clips.append(clip)
        last = end
        count += 1

    if not clips:
        print("No silence detected, exiting...")
        return


    if full_duration - float(last) > minimum_duration:
        print("Clip {} (Start: {}, End: {})".format(count, last, 'EOF'))
        clips.append(video.subclip(last))

    processed_video = concatenate_videoclips(clips)
    processed_video.write_videofile(
        out_path,
        fps=60,
        preset='ultrafast',
        codec='libx264',
        audio_codec='aac'
    )

    video.close()


main()

I won't go over this in full detail, as I did that in the last post about the silence trimming script. I will break down the changes I made.

For a break down of the scripts in more detail, check out the last post I made about it.

Automatically trim silence from video with ffmpeg and python

Donald Feury ・ May 9 '20 ・ 4 min read

#python #ffmpeg #video #productivity

Changes

def generate_timestamps(path, threshold, duration):
    command = "detect_silence {} {} {}".format(input_path, threshold, duration)
    output = subprocess.run(command, shell=True, capture_output=True, text=True)
    return output.stdout.split('\n')[:-1]

Here I created a function to pass in the arguments needed by the detect silence script, and execute it using subprocess.run.

It needs the capture_output=True to actually save the output, and text=True to make the output be in the form of a string, otherwise its returned as raw bytes.

I then split on the newlines and remove the last entry, as its an empty string that is not needed.

Since we are grabbing the script output straight from stdout, we no longer have to open and read an arbitrary text file to get the timestamps.

One last change was, before I was adding a padding to the start of the next clip, to make the transitions less abrupt. Now I add it the end of the last clip, as it seems more natural.

if not clips:
        print("No silence detected, exiting...")
        return

I also added this sanity check to make sure there were actually clips generated, can't concatenate clips that don't exist.

Thats it! Now I can remove the silence parts of a video by calling only script! It also avoids having to create the intermittent timestamp file as well.

Comments

[aproxis]

added some comments

#!/usr/bin/env python

# Import the necessary libraries and modules
import sys
import subprocess
import os
from moviepy.editor import VideoFileClip, concatenate_videoclips

# Read the command-line arguments
input_path = sys.argv[1]
out_path = sys.argv[2]
threshold = sys.argv[3]
duration = sys.argv[4]

# Read the optional fifth command-line argument
try:
    ease = float(sys.argv[5])
# If the fifth argument is not provided, use a default value
except IndexError:
    ease = 0.2

# Set the minimum duration of a clip
minimum_duration = 1.0

# Define a function to generate a list of timestamps for silence periods in the input video
def generate_timestamps(path, threshold, duration):
    # Run the `detect_silence` command-line utility
    command = "detect_silence {} {} {}".format(input_path, threshold, duration)
    output = subprocess.run(command, shell=True, capture_output=True, text=True)
    # Split the output into a list of strings, one for each silence period
    return output.stdout.split('\n')[:-1]

# Define the main function
def main():
    # Initialize some variables
    count = 0
    last = 0
    # Get the list of silence timestamps
    timestamps = generate_timestamps(input_path, threshold, duration)
    # Print the list of timestamps for debugging
    print("Timestamps: {}".format(timestamps))
    # Load the input video
    video = VideoFileClip(input_path)
    # Get the duration of the input video
    full_duration = video.duration
    # Initialize an empty list to store the output video clips
    clips = []

    # Iterate over the list of timestamps
    for times in timestamps:
        # Split the timestamp string into two parts: the end time and the duration
        end,dur = times.strip().split()
        # Print the end time and duration for debugging
        print("End: {}, Duration: {}".format(end, dur))

        # Calculate the start time of the clip based on the end time and duration
        to = float(end) - float(dur) + ease

        # Set the start time of the clip to the last end time
        start = float(last)
        # Calculate the duration of the clip
        clip_duration = float(to) - start
        # Print the clip duration for debugging
        print("Clip Duration: {} seconds".format(clip_duration))

        # If the clip duration is less than the minimum duration, skip this iteration
        if clip_duration < minimum_duration:
            continue

        # If the clip extends past the end of the input video, skip this iteration
        if full_duration - to < minimum_duration:
            continue

        # Print the start and end times of the clip for debugging
        print("Clip {} (Start: {}, End: {})".format(count, start,
        # Create a subclip of the input video using the start and end times
        clip = video.subclip(start, to)
        # Add the clip to the list of output clips
        clips.append(clip)
        # Update the last end time
        last = end
        # Increment the clip count
        count += 1

    # If no clips were added to the list, it means no silence periods were detected
    if not clips:
        # Print an error message and exit the function
        print("No silence detected, exiting...")
        return

    # If the last clip extends past the end of the input video, add a final clip
    if full_duration - float(last) > minimum_duration:
        print("Clip {} (Start: {}, End: {})".format(count, last, 'EOF'))
        clips.append(video.subclip(last))

    # Concatenate the output clips together to create the final video
    processed_video = concatenate_videoclips(clips)
    # Save the final video to the specified output path
    processed_video.write_videofile(
        out_path,
        fps=60,
        preset='ultrafast',
        codec='libx264',
        audio_codec='aac'
    )

    # Close the input video
    video.close()

# Call the main function
main()