A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr

根据数字系统类型返回创建相应的数字系统，默认为 mid NUMBERING_TYPES = ['low', 'mid', 'high']: 中文数字系统类型 low: '兆' = '亿' * '十' = $10^{9}$, '京' = '兆' * '十', et

r"""Puts each data field into a tensor with outer dimension batch size

r"""Puts each data field into a tensor with outer dimension batch size

:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and

:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and

:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and

Computes embeddings for a batch of mel spectrogram. :param frames_batch: a batch mel of spectrogram as a numpy array of float32 of shape

Run evaluation code. :param model: PT model :param dataloaders: list of PT dataloaders :param max_batches: Scalar :pa

Forward evaluation data and calculate statistics. Args: data_loader: object Returns: statistics: dict,

:param x: [B, T, H] :return: [B, T, H]

:param dur_input: [B, T_txt, H] :param mel2ph: [B, T_mel] :param txt_tokens: [B, T_txt] :param ret: :return:

r"""Load list of audio files and return a audio embeddings

attn: bx x L_t x L_s attn_ks: shape: tensor with shape [batch_size], input_lens/output_lens diagonal: y=k*x (k=attn_ks, x:output, y:inpu

Build sinusoidal embeddings. This matches the implementation in tensor2tensor, but differs slightly from the description in Section 3

Build sinusoidal embeddings. This matches the implementation in tensor2tensor, but differs slightly from the description in Section 3

attn: bs x L_t x L_s

Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).

attn: bs x L_t x L_s

r"""Load list of class labels and return text embeddings

:param h: [B, T, H] :param seg_ids: [B, T] :return: h_ph: [B, T_ph, H]

:param h: [B, T, H] :param seg_ids: [B, T] :return: h_ph: [B, T_ph, H]

Initialize a Linear or Convolutional layer.

enumerate available model architectures based on config files

load network parameters from model_file :param model_file: file containing the model parameters

Logs the metric dict passed in. :param metrics: :param grad_norm_dic:

If the signal is almost empty(determined by threshold), if will only be divided by 2**15 :param audio: 1d waveform, 2**15 :param alpha: t