Split large audio file and transcribe it using the Whisper API from OpenAI

transcribe.py

import os
import sys
import openai
import os.path

from dotenv import load_dotenv
from pydub import AudioSegment

load_dotenv()
openai.api_key = os.getenv('OPENAI_API_KEY')

audio = AudioSegment.from_mp3(sys.argv[1])

segment_length = 25 * 60
duration = audio.duration_seconds
print('Segment length: %d seconds' % segment_length)
print('Duration: %d seconds' % duration)

segment_filename = os.path.basename(sys.argv[1])
segment_filename = os.path.splitext(segment_filename)[0]
number_of_segments = int(duration / segment_length)
segment_start = 0
segment_end = segment_length * 1000
enumerate = 1
prompt = ""

for i in range(number_of_segments):
    sound_export = audio[segment_start:segment_end]

    exported_file = '/tmp/' + segment_filename + '-' + str(enumerate) + '.mp3'
    sound_export.export(exported_file, format="mp3")
    print('Exported segment %d of %d' % (enumerate, number_of_segments))

    f = open(exported_file, "rb")
    data = openai.Audio.transcribe("whisper-1", f, prompt=prompt)
    f.close()
    print('Transcribed segment %d of %d' % (enumerate, number_of_segments))

    f = open(os.path.join('transcripts', segment_filename + '.txt'), "a")
    f.write(data.text)
    f.close()

    prompt += data.text
    segment_start += segment_length * 1000
    segment_end += segment_length * 1000
    enumerate += 1