Skip to content

Latest commit

 

History

History
80 lines (64 loc) · 3.22 KB

README.md

File metadata and controls

80 lines (64 loc) · 3.22 KB

Install FFmpeg

https://www.wikihow.com/Install-FFmpeg-on-Windows

Install ffmpeg-python ffmpeg-python API Docs

pip install ffmpeg-python

Play sounds

pip3 install gTTS playsound

import gtts
from playsound import playsound
# play the audio file
playsound("hello.mp3")

Language transalation

import speech_recognition as sr
r = sr.Recognizer()

with sr.AudioFile("hello_world.wav") as source:
    audio = r.record(source)
try:
    s = r.recognize_google(audio)
    print("Text: "+s)
except Exception as e:
    print("Exception: "+str(e))

Remove orginal audio channel from MP4

import subprocess
command = 'for file in *.mp4; do ffmpeg -i "$file" -c copy -an "noaudio_$file"; done'
subprocess.call(command, shell=True)

Combine MP4 and MP3

pip install ffmpeg-python

import ffmpeg
infile1 = ffmpeg.input(combine + "/" + name + ".mp4")
infile2 = ffmpeg.input(combine + "/" + name + ".mp3")
ffmpeg.concat(infile1, infile2, v=1, a=1).output(final_save_path + "/" + name + ".mp4").run()

Text-to-Speech generation

API to retrieve videos and meta data from Youtube

Twitch API to retrieve videos and meta data from Twitch

twitch-python (Current and release recently)

python-twitch-client (rich functionalities, but no update for two years)

5 Manual Ways to Subtitle and Caption Videos Automatically Using Speech Recognition

It's always good ideas to start manually to work out the concept and workflow manully before you developed software and tool to automate them.

Video Captioning API and Code

Sequence to Sequence -- Video to Text

Automated Video Captioning using S2VT

References

Twitch Stream Highlights Detection with Machine Learning