speaker_encoder/tokenizer_ecapa_tdnn.py

"""Dummy tokenizer for pipeline("feature-extraction") compatibility.

The HuggingFace ``FeatureExtractionPipeline`` unconditionally requires a
tokenizer, even for audio models that have no vocabulary.  This thin wrapper
satisfies that interface by delegating ``__call__`` to the real
``EcapaTdnnFeatureExtractor``, which computes log-mel spectrograms from raw
audio.

>>> pipe = pipeline("feature-extraction", model=model_id, trust_remote_code=True)
>>> pipe("audio.wav")  # works!
"""

import os

import numpy as np
from transformers import PreTrainedTokenizer
from transformers.feature_extraction_utils import BatchFeature


class EcapaTdnnDummyTokenizer(PreTrainedTokenizer):
    """Tokenizer shim that wraps :class:`EcapaTdnnFeatureExtractor`.

    This class exists *only* to make ``pipeline("feature-extraction")`` work
    with ECAPA-TDNN speaker encoder models.  It contains no real vocabulary —
    all audio preprocessing is handled by the feature extractor.
    """

    vocab_files_names: dict[str, str] = {}
    model_input_names = ["input_values"]

    def __init__(self, **kwargs):
        # Filter out tokenizer-specific kwargs that don't apply to us
        kwargs.pop("added_tokens_decoder", None)
        super().__init__(**kwargs)

    # -- abstract method stubs (unused but required) -----------------------

    @property
    def vocab_size(self) -> int:
        return 0

    def get_vocab(self) -> dict[str, int]:
        return {}

    def _tokenize(self, text, **kwargs):
        return []

    def _convert_token_to_id(self, token):
        return 0

    def _convert_id_to_token(self, index):
        return ""

    def save_vocabulary(self, save_directory, filename_prefix=None):
        return ()

    # -- the only method that actually matters ------------------------------

    def __call__(self, raw_speech, return_tensors="pt", **kwargs):
        """Preprocess audio via the feature extractor.

        Accepts the same inputs as :class:`EcapaTdnnFeatureExtractor`:
        file paths, numpy arrays, or lists thereof.
        """
        try:
            from .feature_extraction_ecapa_tdnn import EcapaTdnnFeatureExtractor
        except ImportError:
            from feature_extraction_ecapa_tdnn import EcapaTdnnFeatureExtractor

        # Load the feature extractor config from the same directory
        model_dir = os.path.dirname(os.path.abspath(__file__))
        try:
            fe = EcapaTdnnFeatureExtractor.from_pretrained(model_dir)
        except Exception:
            fe = EcapaTdnnFeatureExtractor()

        return fe(raw_speech, return_tensors=return_tensors, **kwargs)