Python script to use Whisper to create srt's for all mp4's that don't currently have one in the current directory.

captions.py

import os
import whisper
from whisper.utils import get_writer

# Get the current directory path
directory = os.getcwd()

# Loop through all the files in the directory
for file in sorted(os.listdir(directory)):
  
  # Check if the file has the mp4 extension
  if file.endswith('.mp4'):
    
    # Get the name of the file with the extension
    name = os.path.splitext(file)[0] + '.mp4'
    srt_file = directory + '/' + name + '.srt'
    
    # Check if there is a related srt file
    if not os.path.isfile(srt_file):
      
      # Create srt for all mp4 files that need one
      print('Processing ' + file + '...')
      model = whisper.load_model('large')
      result = model.transcribe(file, fp16=False)
      srt_writer = get_writer('srt', './')
      srt_writer(result, file)

requirements.txt

openai-whisper

Hi, I tried to run your script and got an "out of memory" error. I think it is due to the fact that the line "model = whisper.load_model('large')" is part of the loop (and so the program attempts to load the model several times). I fixed it by moving the line outside the loop, as follows:

import os
import whisper
from whisper.utils import get_writer

model = whisper.load_model('large')

# Get the current directory path
directory = os.getcwd()

# Loop through all the files in the directory
for file in sorted(os.listdir(directory)):
  
  # Check if the file has the mp4 extension
  if file.endswith('.mp4'):
    
    # Get the name of the file with the extension
    name = os.path.splitext(file)[0] + '.mp4'
    srt_file = directory + '/' + name + '.srt'
    
    # Check if there is a related srt file
    if not os.path.isfile(srt_file):
      
      # Create srt for all mp4 files that need one
      print('Processing ' + file + '...')
      result = model.transcribe(file, fp16=False)
      srt_writer = get_writer('srt', './')
      srt_writer(result, file)