Functions — github.com/athena-team/athena

CodeHub MCPcopy Create free account

hub / github.com/athena-team/athena / functions

Functions3,518 in github.com/athena-team/athena

⨍ Functions 3,518◇ Types & classes 359↳ Endpoints 1

(self, d_model, kernel_size=17, causal=True,

athena/layers/u2/conv_module_u2.py:44

(self, encoder_layers, static_chunk_size: int = 0, use_dyna

athena/layers/u2/transformer_u2.py:175

(self, decoder_layers)

athena/layers/u2/transformer_u2.py:223

( self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation="gelu" )

athena/layers/u2/transformer_u2_layer.py:160

Construct an Conv2dSubsampling4 object.

athena/layers/u2/subsampling.py:48

( self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation="gelu" )

athena/layers/u2/conformer_u2_layer.py:178

(self, encoder_layers, static_chunk_size: int = 0, use_dyna

athena/layers/u2/conformer_u2.py:174

(self, decoder_layers)

athena/layers/u2/conformer_u2.py:365

(self, d_model, max_position=5000, dropout_rate=0.0, scale=False)

athena/layers/u2/embedding.py:26

(self, **kwargs)

athena/models/base.py:27

(self, data_descriptions, config=None)

athena/models/masked_pc.py:57

(self, data_descriptions, config=None)

athena/models/asr/mtl_seq2seq.py:52

(self, data_descriptions, config=None)

athena/models/asr/speech_u2.py:751

(self, data_descriptions, config=None)

athena/models/asr/speech_u2.py:810

(self, data_descriptions, config=None)

athena/models/asr/av_mtl_seq2seq.py:49

(self, data_descriptions, config=None)

athena/models/asr/av_conformer.py:58

(self, data_descriptions, config=None)

athena/models/asr/speech_transformer.py:61

(self, data_descriptions, config=None)

athena/models/asr/speech_conformer.py:60

(self, data_descriptions, config=None)

athena/models/asr/speech_conformer_ctc.py:57

(self, data_descriptions, config=None)

athena/models/vad/vad_dnn.py:37

Initialize TFReflectionPad1d module. Args: padding_size (int) padding_type (str) ("CONSTANT", "REFLECT", or "SYMMETRI

athena/models/vad/vad_marblenet.py:30

Initialize BNResidualBlock module. Args: kernel_size (int): Kernel size. filters (int): Number of filters.

athena/models/vad/vad_marblenet.py:57

athena/models/vad/vad_marblenet.py:189

config including the params for build lm

athena/models/lm/rnn_lm.py:41

config including the params for build lm

athena/models/lm/nn_lm.py:32

(self, lm_path)

athena/models/lm/kenlm.py:26

config including the params for build lm

athena/models/lm/transformer_lm.py:42

Initialize duration calculator

athena/models/tts/fastspeech2.py:184

(self, hparams, **kwargs)

athena/models/tts/fastspeech2.py:222

(self, data_descriptions, config=None)

athena/models/tts/tts_transformer.py:70

athena/models/tts/fastspeech.py:333

Initialize duration calculator Args: teacher_model: the pretrained model used to calculate durations and outputs. tea

athena/models/tts/fastspeech.py:432

(self, data_descriptions, config=None)

athena/models/tts/tacotron2.py:78

(self, data_descriptions, config=None)

athena/models/kws/cnn_wakeup.py:37

(self, data_descriptions, config=None)

athena/models/kws/transformer_wakeup_2dense.py:43

(self, data_descriptions, config=None)

athena/models/kws/conformer_wakeup.py:44

(self, **kwargs)

athena/models/kws/base.py:27

(self, data_descriptions, config=None)

athena/models/kws/misp_wakeup.py:37

(self, data_descriptions, config=None)

athena/models/kws/dnn_wakeup.py:37

(self, data_descriptions, config=None)

athena/models/kws/transformer_wakeup_resnet.py:43

(self, data_descriptions, config=None)

athena/models/kws/transformer_wakeup_focal_loss.py:43

(self, data_descriptions, config=None)

athena/models/kws/transformer_wakeup.py:43

(self, data_descriptions, config=None)

athena/models/kws/transformer_wakeup_average_pooling.py:43

(self, data_descriptions, config=None)

athena/models/kws/crnn_wakeup.py:37

(self, data_descriptions, config=None)

athena/models/kws/transformer_av_wakeup.py:43

Init config of AudioFeaturizer. Args: config: 'type': The name of the feature you want to extract. That is, '

athena/transform/audio_featurizer.py:40

(self, config: dict)

athena/transform/feats/mel_spectrum.py:41

(self, config: dict)

athena/transform/feats/read_wav.py:38

(self, config: dict)

athena/transform/feats/add_rir_noise_aecres.py:30

athena/transform/feats/base_frontend.py:25

(self, config: dict)

athena/transform/feats/base_frontend.py:37

(self, config: dict)

athena/transform/feats/pitch.py:39

(self, config: dict)

athena/transform/feats/framepow.py:38

(self, config: dict)

athena/transform/feats/spectrum.py:41

(self, config: dict)

athena/transform/feats/mfcc.py:41

(self, config: dict)

athena/transform/feats/write_wav.py:36

(self, config: dict)

athena/transform/feats/cmvn.py:40

(self, config: dict)

athena/transform/feats/fbank.py:41

(self, config: dict)

athena/transform/feats/fbank_pitch.py:36

examples/tts/data_baker/local/extract_feat.py:29

athena/utils/num_elements_batch_sampler.py:167

athena/utils/num_elements_batch_sampler.py:164

athena/data/text_featurizer.py:149

athena/data/text_featurizer.py:199

athena/data/text_featurizer.py:257

athena/data/datasets/base.py:145

athena/data/datasets/asr/speech_recognition_batch_bins_kaldiio.py:209

athena/data/datasets/asr/audio_video_recognition_batch_bins.py:201

athena/data/datasets/asr/speech_recognition_batch_bins.py:166

athena/utils/hparam.py:640

athena/utils/num_elements_batch_sampler.py:154

Method_default_unk_index

athena/data/text_featurizer.py:78

Method_default_unk_symbol

athena/data/text_featurizer.py:81

Function_expand_decimal_point

examples/tts/ljspeech/local/prepare_data.py:56

Function_expand_dollars

examples/tts/ljspeech/local/prepare_data.py:59

Function_expand_number

examples/tts/ljspeech/local/prepare_data.py:82

Function_expand_ordinal

examples/tts/ljspeech/local/prepare_data.py:79

Method_forward_encoder_log_ctc

(self, samples, final_layer, training: bool = None)

athena/models/asr/speech_transformer.py:175

Method_forward_encoder_log_ctc

(self, samples, final_layer, training: bool = None)

athena/models/asr/speech_conformer.py:172

Method_forward_encoder_log_ctc

(self, samples, training: bool = None)

athena/models/asr/speech_conformer_ctc.py:153

Function_gen_data

multi thread loader

athena/data/datasets/base.py:37

Function_gen_data

multi thread loader

athena/data/datasets/asr/speech_recognition_batch_bins_kaldiio.py:36

Function_gen_data

multi thread loader

athena/data/datasets/asr/audio_video_recognition_batch_bins.py:36

Function_gen_data

multi thread loader

athena/data/datasets/asr/speech_recognition_batch_bins.py:36

Method_get_kind_name

Returns the field name given parameter type and is_list. Args: param_type: Data type of the hparam. is_list: Whether

athena/utils/hparam.py:644

Function_progress

(count, block_size, total_size)

examples/asr/librispeech/local/prepare_data.py:63

Function_progress

(count, block_size, total_size)

examples/tts/ljspeech/local/prepare_data.py:193

Function_progress

(count, block_size, total_size)

examples/tts/data_baker/local/prepare_data.py:226

Function_remove_commas

examples/tts/ljspeech/local/prepare_data.py:53

runtime/server/x86/cppflow/raw_ops.h:26

Functionaccumulate_n_v2

runtime/core/cppflow/raw_ops.h:50

Functionaccumulate_n_v2

runtime/server/x86/cppflow/raw_ops.h:50

Functionaccumulator_num_accumulated

runtime/core/cppflow/raw_ops.h:80

Functionaccumulator_num_accumulated

runtime/server/x86/cppflow/raw_ops.h:80

Functionaccumulator_take_gradient

runtime/core/cppflow/raw_ops.h:104

Functionaccumulator_take_gradient

runtime/server/x86/cppflow/raw_ops.h:104

runtime/core/cppflow/raw_ops.h:132

runtime/server/x86/cppflow/raw_ops.h:132

runtime/core/cppflow/raw_ops.h:156

runtime/server/x86/cppflow/raw_ops.h:156

← previous next →1,101–1,200 of 3,518, ranked by callers