paddlespeech.t2s.frontend.g2pw.dataset module

Credits

This code is modified from https://github.com/GitYCC/g2pW

paddlespeech.t2s.frontend.g2pw.dataset.get_char_phoneme_labels(polyphonic_chars: List[List[str]]) → Tuple[List[str], Dict[str, List[int]]]

paddlespeech.t2s.frontend.g2pw.dataset.get_phoneme_labels(polyphonic_chars: List[List[str]]) → Tuple[List[str], Dict[str, List[int]]]

paddlespeech.t2s.frontend.g2pw.dataset.prepare_onnx_input(tokenizer, labels: List[str], char2phonemes: Dict[str, List[int]], chars: List[str], texts: List[str], query_ids: List[int], use_mask: bool = False, window_size: Optional[int] = None, max_len: int = 512) → Dict[str, array]