Pass the input through the encoder layer. Args: src: the sequence to the encoder layer (required). src_mask: tf.zero

Pass the inputs (and mask) through the decoder layer. Args: tgt: the sequence to the decoder layer (required). memory

Subsample x. Args: x (tf.Tensor): Input tensor (#batch, time, idim, 1). x_mask (tf.Tensor): Input mask (#batch, 1, 1,

Pass the input through the encoder layer. Args: src: the sequence to the encoder layer (required). src_mask: tf.zero

Pass the inputs (and mask) through the decoder layer. Args: tgt: the sequence to the decoder layer (required). memory

Take in and process masked source/target sequences. Args: src: the sequence to the encoder (required). tgt: the seque

Pass the input through the endocder layers in turn. Args: src: the sequnce to the encoder (required). mask: the mask

Pass the inputs (and mask) through the decoder layer in turn. Args: tgt: the sequence to the decoder (required). memo

call function

call model

used for training Args: samples is a dict, including keys: 'input', 'input_length', 'output_length', 'output' in

call function in keras layers

call function in keras layers

Calculate forward propagation. Args: x (Tensor): Input tensor (B, T, C). Returns: Tensor: Padded tensor (B, T

Calculate forward propagation. Args: x (Tensor): Input tensor (B, T, C). Returns: Tensor: Output tensor (B, T,

Calculate forward propagation. Args: x (Tensor): Input tensor (B, T, C). Returns: Tensor: Output tensor (B, T,

Args: samples: samples from dataset Returns:: durations: Batch of durations shape: [batch, max_input_length)

Calculate replicated sequences based on duration sequences Args: phoneme_sequences: sequences of phoneme features, shape: [batch,

Args: samples: samples from dataset Returns:: durations: Batch of durations shape: [batch, max_input_length)

call model

Caculate logmelspectrum of audio data. Args: audio_data: the audio signal from which to compute spectrum. sample_rate

Get audio data and sample rate from a wavfile. Args: wavfile: filepath of wav. speed: Speed of sample channels wanted

Caculate power spectrum or log power spectrum of audio data. :param audio_data: the audio signal from which to compute spectrum.

Caculate pitch && POV features features of audio data. Args: audio_data: the audio signal from which to compute mfcc.

Caculate power of every frame in speech. Args: audio_data: the audio signal from which to compute spectrum. sample_ra

Caculate power spectrum or log power spectrum of audio data. Args: audio_data: the audio signal from which to compute spectrum.

Caculate mfcc features of audio data. Args: audio_data: the audio signal from which to compute mfcc. sample_rate: the

Write wav using audio_data. Args: filename: filepath of wav. audio_data: a tensor containing data of a wav.

Compute CMVN on features.

Caculate fbank features of audio data. Args: audio_data: the audio signal from which to compute spectrum. sample_rate

Caculate fbank && pitch(concat) features of wav. Args: audio_data: the audio signal from which to compute mfcc. sampl

complex abs

complex number averaging

function implementations */ --------------------------------------------------- complex FIR filtering of 2nd dimension data len : Tap length

--------------------------------------------------- CmplxDataPush : push complex data into 2nd dimension bufer in len bufer length xin input

complex division

complex division 2

complex generation

complex sqrt

complex subtraction

compute autocorrelation */

vitural interface

compute cmvn file