Speech Recognition Model & Transcription Engine

Complete speech-to-text system with audio processing, multilingual support.

# Source: https://github.com/mperkins0155/whisper | License: MIT | Copyright 2022 OpenAI
# Provided via justclaw.it.com; keep this notice with the code.
import argparse
import os
import traceback
import warnings
from typing import TYPE_CHECKING, List, Optional, Tuple, Union

import numpy as np
import torch
import tqdm

from .audio import (
    FRAMES_PER_SECOND,
    HOP_LENGTH,
    N_FRAMES,
    N_SAMPLES,
    SAMPLE_RATE,
    log_mel_spectrogram,
    pad_or_trim,
)
from .decoding import DecodingOptions, DecodingResult
from .timing import add_word_timestamps
from .tokenizer import LANGUAGES, TO_LANGUAGE_CODE, get_tokenizer
from .utils import (
    exact_div,
    format_timestamp,
    get_end,
    get_writer,
    make_safe,
    optional_float,
    optional_int,
    str2bool,
)

if TYPE_CHEC

... (truncated -- full source via MCP)