API documentation

• models
  • model
  • encoder_decoder
  • speech2text
  • text2text
  • text2speech
  • text2speech_centaur
  • text2speech_tacotron
  • text2speech_wavenet
  • image2label
• data
  • image2label
    • image2label
    • imagenet_preprocessing
  • speech2text
    • speech2text
    • speech_commands
    • speech_utils
  • text2text
    • t2t
    • text2text
    • tokenizer
  • text2speech
    • text2speech
    • text2speech_wavenet
    • speech_utils
  • data_layer
  • utils
• encoders
  • encoder
  • ds2_encoder
  • tdnn_encoder
  • rnn_encoders
  • transformer_encoder
  • convs2s_encoder
  • resnet_encoder
  • resnet_blocks
  • cnn_encoder
  • tacotron2_encoder
  • wavenet_encoder
  • centaur_encoder
• decoders
  • decoder
  • fc_decoders
  • rnn_decoders
  • transformer_decoder
  • convs2s_decoder
  • tacotron2_decoder
  • centaur_decoder
• losses
  • loss
  • ctc_loss
  • sequence_loss
  • cross_entropy_loss
  • text2speech_loss
  • wavenet_loss
• optimizers
  • optimizers
  • mp_wrapper
  • automatic_loss_scaler
  • lr_policies
• parts
  • rnns
    • attention_wrapper
    • flstm
    • glstm
    • gnmt
    • rnn_beam_search_decoder
    • slstm
    • utils
    • zoneout
  • transformer
    • attention_layer
    • beam_search
    • common
    • embedding_layer
    • ffn_layer
    • utils
  • convs2s
    • attention_wn_layer
    • conv_wn_layer
    • ffn_wn_layer
  • cnns
    • conv_blocks
  • tacotron
    • tacotron_decoder
    • tacotron_helper
  • centaur
    • attention
    • batch_norm
    • conv_block
    • prenet
• utils
  • funcs
  • hooks
  • utils