o *iW@sddlmZddlmZmZmZddlZddlmZddlm Z gZ e   ddededeed eed e d eeeff d d Z eGdddZ ddeded e d ee fddZdS)) dataclass)ListOptionalTupleN)Tensor)fail_if_no_align log_probstargets input_lengthstarget_lengthsblankreturnc Cs||vr td|dt||jdkrtd|dur5|d|d}}tj|f|tj|jd}|durP|d|d}}tj|f|tj|jd}|dusVJ|dus\Jtjj |||||\}}||fS) aAlign a CTC label sequence to an emission. .. devices:: CPU CUDA .. properties:: TorchScript Args: log_probs (Tensor): log probability of CTC emission output. Tensor of shape `(B, T, C)`. where `B` is the batch size, `T` is the input length, `C` is the number of characters in alphabet including blank. targets (Tensor): Target sequence. Tensor of shape `(B, L)`, where `L` is the target length. input_lengths (Tensor or None, optional): Lengths of the inputs (max value must each be <= `T`). 1-D Tensor of shape `(B,)`. target_lengths (Tensor or None, optional): Lengths of the targets. 1-D Tensor of shape `(B,)`. blank_id (int, optional): The index of blank symbol in CTC emission. (Default: 0) Returns: Tuple(Tensor, Tensor): Tensor: Label for each time step in the alignment path computed using forced alignment. Tensor: Log probability scores of the labels for each time step. Note: The sequence length of `log_probs` must satisfy: .. math:: L_{\text{log\_probs}} \ge L_{\text{label}} + N_{\text{repeat}} where :math:`N_{\text{repeat}}` is the number of consecutively repeated tokens. For example, in str `"aabbc"`, the number of repeats are `2`. Note: The current version only supports ``batch_size==1``. z4targets Tensor shouldn't contain blank index. Found .z2targets values must be less than the CTC dimensionNr)Zdtypedevice) ValueErrortorchmaxshapesizefullZint64ropsZ torchaudio forced_align) rr r r r Z batch_sizelengthpathsscoresro/var/www/html/eduruby.in/lip-sync/lip-sync-env/lib/python3.10/site-packages/torchaudio/functional/_alignment.pyr s-  rc@sHeZdZUdZeed< eed< eed< eed< defddZd S) TokenSpanz[TokenSpan() Token with time stamps and score. Returned by :py:func:`merge_tokens`. tokenstartendscorer cCs |j|jS)zReturns the time span)r"r!)selfrrr__len__[s zTokenSpan.__len__N)__name__ __module__ __qualname____doc__int__annotations__floatr%rrrrrLs rtokensrcsjdks jdkrtdttkrtdtjtjdgjdtjdgjdd}t|dk } fdd t |d d|dd D}|S) aRemoves repeated tokens and blank tokens from the given CTC token sequence. Args: tokens (Tensor): Alignment tokens (unbatched) returned from :py:func:`forced_align`. Shape: `(time, )`. scores (Tensor): Alignment scores (unbatched) returned from :py:func:`forced_align`. Shape: `(time, )`. When computing the token-size score, the given score is averaged across the corresponding time span. Returns: list of TokenSpan Example: >>> aligned_tokens, scores = forced_align(emission, targets, input_lengths, target_lengths) >>> token_spans = merge_tokens(aligned_tokens[0], scores[0]) rz(`tokens` and `scores` must be 1D Tensor.z.`tokens` and `scores` must be the same length.r)r)prependappendrc s@g|]\}}|krt||||dqS))r r!r"r#)rmeanitem).0r!r"r rr r-rr {s z merge_tokens..N) ndimrlenrdiffZtensorrZnonzeroZsqueezetolistzip)r-rr r7Zchanges_wo_blankspansrr3r merge_tokens`s"r;)NNr)r) dataclassesrtypingrrrrrZtorchaudio._extensionr__all__r*rrr;rrrrs4     @$