whisperx mode

import whisperx as wx
from pydub import AudioSegment
import os
from dotenv import load_dotenv
from config import AUDIO_FILE_DIR

# Load .env file if present
load_dotenv()
device = "cuda"
batch_size = 16
compute_type = "int8"
model_dir = "C:\\test"
language = "en"
model = wx.load_model("tiny", device, language=language, compute_type=compute_type, download_root=model_dir)

def transcribe_audio(file_path):
    try:
        audio = AudioSegment.from_file(f"{AUDIO_FILE_DIR}/{file_path}")
        chunk_size = 10 * 60 * 1000
        num_chunks = len(audio) // chunk_size + (1 if len(audio) % chunk_size else 0)
        transcript = ""
        file_size = os.path.getsize(f"{AUDIO_FILE_DIR}/{file_path}")

        if file_size <= 24 * 1024 * 1024:
            result = model.transcribe(f"{AUDIO_FILE_DIR}/{file_path}", batch_size=batch_size)
            for segment in result['segments']:
                transcript += segment['text'] + " "
        else:
            for i in range(num_chunks):
                temp_chunk_path = f"{AUDIO_FILE_DIR}/temp_chunk.mp3"
                chunk = audio[i*chunk_size:(i+1)*chunk_size]
                with open(temp_chunk_path, 'wb') as f:
                    chunk.export(f, format="mp3")
                try:
                    result = model.transcribe(temp_chunk_path, batch_size=batch_size)
                    for segment in result['segments']:
                        transcript += segment['text'] + " "
                finally:
                    os.remove(temp_chunk_path)

        os.remove(f"{AUDIO_FILE_DIR}/{file_path}")

        return transcript

    except FileNotFoundError as e:
        raise FileNotFoundError(f"The audio file {file_path} was not found.") from e
    except Exception as e:
        raise Exception(f"An error occurred during the transcription process: {e}") from e