Function _is_audio_container

funasr/utils/load_utils.py:178–204

Return True if *data* starts with a recognised container-format magic header. Raw PCM byte streams have no header, so they will return False and the expensive pydub/ffmpeg validation round-trip can be skipped entirely.

(data: bytes)

def _is_audio_container(data: bytes) -> bool:
    """Return True if *data* starts with a recognised container-format magic header.

    Raw PCM byte streams have no header, so they will return False and the
    expensive pydub/ffmpeg validation round-trip can be skipped entirely.
    """
    if len(data) < 4:
        return False
    # WAV  – RIFF....WAVE
    if data[:4] == b"RIFF":
        return True
    # MP3  – ID3 tag or sync word (0xFF 0xEx)
    if data[:3] == b"ID3" or (data[0] == 0xFF and (data[1] & 0xE0) == 0xE0):
        return True
    # OGG
    if data[:4] == b"OggS":
        return True
    # FLAC
    if data[:4] == b"fLaC":
        return True
    # MP4 / M4A / AAC  – 'ftyp' box at offset 4
    if len(data) >= 8 and data[4:8] == b"ftyp":
        return True
    # WebM / MKV
    if data[:4] == b"\x1a\x45\xdf\xa3":
        return True
    return False


def load_bytes(input):