splytter.py audio splitter

splytter.py

from pydub import AudioSegment
from openai import OpenAI


def split_audio_into_chunks(filename, chunk_duration=600000):
    audio = AudioSegment.from_file(filename)
    chunk_length = len(audio)
    start = 0
    chunk_filenames = []
    i = 0
    while start < chunk_length:
        end = start + chunk_duration
        chunk = audio[start:end]
        chunk_filename = f'chunk_{i+1}.mp3'
        chunk.export(chunk_filename, format='mp3')
        chunk_filenames.append(chunk_filename)
        start += chunk_duration
        i += 1
    return chunk_filenames


target_file = './files/2.mp4'
chunks = split_audio_into_chunks(target_file)
transcriptions = []
client = OpenAI()
client.api_key = 'sk-superSecret'
for i, chunkz in enumerate(chunks):
    audio_file= open(chunks[i], "rb")
    transcription = client.audio.transcriptions.create(model="whisper-1", file=audio_file)
    transcriptions.append(transcription.text)

with open('transcription.txt', 'w', encoding='utf-8') as file:
    for transcription in transcriptions:
        file.write(transcription + '\n')