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
↓ 1 callersMethodCompute
Compute fbank feat, return num frames
runtime/server/x86/frontend/fbank.h:130
↓ 1 callersFunctionComputeCorrelation
athena/transform/feats/ops/kernels/pitch.cc:73
↓ 1 callersFunctionComputeKaldiPitch
athena/transform/feats/ops/kernels/pitch.cc:1025
↓ 1 callersFunctionComputeKaldiPitchFirstPass
athena/transform/feats/ops/kernels/pitch.cc:979
↓ 1 callersFunctionComputeLocalCost
athena/transform/feats/ops/kernels/pitch.cc:136
↓ 1 callersMethodConvProcess
athena/transform/feats/ops/kernels/CConv.cc:110
↓ 1 callersMethodElapsed
return int in milliseconds
runtime/server/x86/utils/timer.h:27
↓ 1 callersMethodGetData
get part of the wave data to process */
runtime/core/frontend/audio_pack_sim.h:60
↓ 1 callersMethodGetData
get part of the wave data to process */
runtime/server/x86/frontend/audio_pack_sim.h:60
↓ 1 callersMethodGetEncoderOutputs
runtime/core/decoder/ctc_decodable.h:85
↓ 1 callersMethodGetEncoderOutputs
runtime/server/x86/decoder/ctc_decodable.h:85
↓ 1 callersMethodGetGraph
runtime/core/inference/tensor_model.h:202
↓ 1 callersMethodGetGraph
runtime/server/x86/inference/tensor_model.h:202
↓ 1 callersFunctionGetHostname
runtime/server/x86/server/server.cc:41
↓ 1 callersMethodGetLogits
runtime/core/decoder/ctc_decodable.h:82
↓ 1 callersMethodGetLogits
runtime/server/x86/decoder/ctc_decodable.h:82
↓ 1 callersMethodGetNBestPath
runtime/core/decoder/ctc_faster_decoder.cc:120
↓ 1 callersMethodGetNBestPath
runtime/server/x86/decoder/ctc_faster_decoder.cc:120
↓ 1 callersMethodGetRescoringNnet
runtime/core/inference/tensor_model.h:85
↓ 1 callersMethodGetRescoringNnet
runtime/server/x86/inference/tensor_model.h:85
↓ 1 callersMethodGetResult
runtime/server/x86/inference/e2e_context.h:39
↓ 1 callersMethodGetTraceid
runtime/server/x86/server/server.cc:149
↓ 1 callersMethodInit
runtime/core/frontend/wav.h:51
↓ 1 callersMethodInit
runtime/server/x86/frontend/wav.h:51
↓ 1 callersFunctionInitDecodeOptionsFromFlags
runtime/core/inference/interface.cc:56
↓ 1 callersFunctionInitDecodeOptionsFromFlags
runtime/server/x86/inference/interface.cc:56
↓ 1 callersFunctionInitGlobalResource
runtime/server/x86/server/server.cc:33
↓ 1 callersMethodInvokeDecoder
runtime/core/inference/e2e_context.cc:43
↓ 1 callersMethodInvokeDecoder
runtime/server/x86/inference/e2e_context.cc:43
↓ 1 callersMethodIsLastFrame
runtime/core/decoder/ctc_decodable.h:72
↓ 1 callersMethodIsLastFrame
runtime/server/x86/decoder/ctc_decodable.h:72
↓ 1 callersFunctionLcm
athena/transform/feats/ops/kernels/support_functions.cc:675
↓ 1 callersMethodLoadFst
runtime/core/inference/tensor_model.h:132
↓ 1 callersMethodLoadFst
runtime/server/x86/inference/tensor_model.h:132
↓ 1 callersFunctionNewContextInterfacePtr
runtime/core/inference/interface.cc:114
↓ 1 callersFunctionNewContextInterfacePtr
runtime/server/x86/inference/interface.cc:114
↓ 1 callersFunctionNewDecoderResourcePtr
runtime/server/x86/inference/interface.cc:83
↓ 1 callersMethodOnReceiveMessage
runtime/server/x86/server/server.cc:77
↓ 1 callersMethodOnSessionClose
runtime/server/x86/server/server.cc:121
↓ 1 callersMethodPushBack
runtime/core/frontend/recycling_vector.cc:45
↓ 1 callersMethodPushBack
runtime/server/x86/frontend/recycling_vector.cc:45
↓ 1 callersFunctionRandGauss
athena/transform/feats/ops/kernels/support_functions.h:160
↓ 1 callersFunctionReadGraph
runtime/core/fst/graph_io.cc:55
↓ 1 callersFunctionReadGraph
runtime/server/x86/fst/graph_io.cc:55
↓ 1 callersFunctionResampleWaveform
athena/transform/feats/ops/kernels/resample.cc:304
↓ 1 callersMethodReset
athena/transform/feats/ops/kernels/resample.cc:184
↓ 1 callersMethodReset
runtime/core/utils/timer.h:25
↓ 1 callersMethodReset
runtime/server/x86/utils/timer.h:25
↓ 1 callersMethodSearch
runtime/core/decoder/ctc_prefix_beam_search.cc:63
↓ 1 callersMethodSearch
runtime/server/x86/decoder/ctc_prefix_beam_search.cc:63
↓ 1 callersMethodSelectH
athena/transform/feats/ops/kernels/CConv.cc:61
↓ 1 callersFunctionSelectLags
athena/transform/feats/ops/kernels/pitch.cc:122
↓ 1 callersMethodSetFinal
runtime/core/fst/athena_fst.h:114
↓ 1 callersMethodSetFinal
runtime/server/x86/fst/athena_fst.h:114
↓ 1 callersMethodSetNccfPov
athena/transform/feats/ops/kernels/pitch.cc:220
↓ 1 callersMethodSetStart
runtime/core/fst/athena_fst.h:113
↓ 1 callersMethodSetStart
runtime/server/x86/fst/athena_fst.h:113
↓ 1 callersMethodSetValue
runtime/core/fst/athena_fst.h:41
↓ 1 callersMethodSetValue
runtime/server/x86/fst/athena_fst.h:41
↓ 1 callersMethodSize
Returns current number of hash buckets.
runtime/core/utils/hash_list.h:112
↓ 1 callersMethodSize
Returns current number of hash buckets.
runtime/server/x86/utils/hash_list.h:112
↓ 1 callersMethodStart
runtime/core/fst/athena_fst.h:109
↓ 1 callersMethodStart
runtime/server/x86/fst/athena_fst.h:109
↓ 1 callersMethodThread
runtime/core/utils/thread_pool.h:40
↓ 1 callersFunctionTopK
runtime/core/utils/utils.cc:50
↓ 1 callersFunctionTopK
runtime/server/x86/utils/utils.cc:50
↓ 1 callersMethodType
runtime/core/inference/resource.h:56
↓ 1 callersMethodType
runtime/server/x86/inference/resource.h:56
↓ 1 callersMethod__call__
(self, logits, samples, logit_length=None)
athena/loss.py:35
↓ 1 callersMethod__impl
Call OP of features to extract features. Args: audio: a tensor of audio data or audio file sr: a tensor of sample rat
athena/transform/audio_featurizer.py:85
↓ 1 callersMethod__init__
(self, cmvn_file=None)
athena/data/feature_normalizer.py:37
↓ 1 callersMethod__init__
Initialize vocabulary. Args: vocab_file: Vocabulary file name.
athena/data/text_featurizer.py:34
↓ 1 callersMethod__init__
(self, config=None)
athena/data/datasets/base.py:126
↓ 1 callersMethod__init__
initialization of multihead attention block Args: d_model: dimension of multi-head attention num_heads: number of att
athena/layers/u2/attention_u2.py:97
↓ 1 callersMethod__init__
( self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation="gelu", unidirec
athena/layers/u2/transformer_u2_layer.py:45
↓ 1 callersMethod__init__
(self)
athena/layers/u2/subsampling.py:25
↓ 1 callersMethod__init__
( self, d_model, nhead, cnn_module_kernel=15, dim_feedforward=2048, dropout=0.1, activation="gelu"
athena/layers/u2/conformer_u2_layer.py:49
↓ 1 callersMethod__len__
(self)
athena/data/text_featurizer.py:84
↓ 1 callersMethod_add_beta_weight
(self, input_shape)
athena/layers/commons.py:295
↓ 1 callersMethod_add_gamma_weight
(self, input_shape)
athena/layers/commons.py:279
↓ 1 callersMethod_apply_normalization
(self, reshaped_inputs, input_shape)
athena/layers/commons.py:201
↓ 1 callersMethod_calculate_t2_attentions
Calculate outputs and attention weights based on tacotron2 Args: samples: samples from dataset Returns::
athena/models/tts/fastspeech.py:483
↓ 1 callersMethod_calculate_transformer_attentions
Calculate outputs and attention weights based on tts transformer Args: samples: samples from dataset Returns::
athena/models/tts/fastspeech.py:498
↓ 1 callersMethod_check_axis
(self)
athena/layers/commons.py:264
↓ 1 callersMethod_check_if_input_shape_is_none
(self, input_shape)
athena/layers/commons.py:234
↓ 1 callersMethod_check_size_of_dimensions
(self, input_shape)
athena/layers/commons.py:249
↓ 1 callersMethod_compare_and_save_best
compare and save the best model with best_loss and N best metrics
athena/utils/checkpoint.py:127
↓ 1 callersMethod_create_attention_masks
masks created by attention location Args: input_length: shape: [batch_size] output_length: shape: [batch_size]
athena/loss.py:211
↓ 1 callersMethod_create_broadcast_shape
(self, input_shape)
athena/layers/commons.py:311
↓ 1 callersMethod_create_input_spec
(self, input_shape)
athena/layers/commons.py:272
↓ 1 callersMethod_create_length_masks
masks created by input and output length Args: input_length: shape: [batch_size] output_length: shape: [batch_size]
athena/loss.py:241
↓ 1 callersMethod_encoder_forward_chunk_by_chunk
Forward input chunk by chunk with chunk_size like a streaming fashion Here we should pay special attention to computation cache
athena/models/asr/speech_u2.py:268
↓ 1 callersMethod_file_compatible
Convert n_best file to CSV file Add "index" and "Accuracy" for no csv n_best file.
athena/utils/checkpoint.py:88
↓ 1 callersMethod_forward_decoder
(self, encoder_out, encoder_mask, hyps_pad, output_mask)
athena/models/asr/speech_u2.py:339
↓ 1 callersMethod_forward_encoder
(self, speech, speech_length, training=None)
athena/models/asr/speech_conformer_ctc.py:145
↓ 1 callersMethod_forward_encoder_log_ctc
(self, samples, training: bool = None)
athena/models/asr/mtl_seq2seq.py:113
↓ 1 callersMethod_forward_transformer_encoder
(self, x, x_mask, training=None)
athena/models/asr/speech_u2.py:155
↓ 1 callersMethod_get_nfft
n_fft is an exponential power of 2 closest to and larger than win_length
athena/tools/vocoder.py:47
↓ 1 callersMethod_get_reshaped_weights
(self, input_shape)
athena/layers/commons.py:223
↓ 1 callersMethod_griffin_lim
Convert linear spectrogram into waveform Args: linear_feats: linear spectrogram gl_iters: num of gl iterations
athena/tools/vocoder.py:86
← previousnext →301–400 of 3,518, ranked by callers