MCPcopy Index your code

hub / github.com/KrishnaDN/x-vector-pytorch / functions

Functions25 in github.com/KrishnaDN/x-vector-pytorch

⨍ Functions 25◇ Types & classes 5
↓ 3 callersFunctionFE_pipeline
(feature_list,store_loc,mode)
feature_extraction.py:19
↓ 3 callersFunctioncreate_meta
(files_list,store_loc,mode='train')
datasets.py:17
↓ 2 callersFunctionlin_spectogram_from_wav
(wav, hop_length, win_length, n_fft=512)
utils/utils.py:26
↓ 2 callersFunctionload_wav
(audio_filepath, sr, min_dur_sec=4)
utils/utils.py:9
↓ 1 callersFunctionextract_features
(audio_filepath)
feature_extraction.py:13
↓ 1 callersFunctionextract_files
(folder_path)
datasets.py:42
↓ 1 callersFunctiontrain
(dataloader_train,epoch)
training_xvector.py:61
↓ 1 callersFunctionvalidation
(dataloader_val,epoch)
training_xvector.py:95
Method__getitem__
(self, idx)
SpeechDataGenerator.py:27
Method__getitem__
(self, idx)
SpeechDataGenerator_precomp_feats.py:27
Method__init__
Read the textfile and get the paths
SpeechDataGenerator.py:15
Method__init__
Read the textfile and get the paths
SpeechDataGenerator_precomp_feats.py:15
Method__init__
TDNN as defined by https://www.danielpovey.com/files/2015_interspeech_multisplice.pdf Affine transformation not applied globally to
models/tdnn.py:13
Method__init__
(self, input_dim = 40, num_classes=8)
models/x_vector.py:17
Method__init__
(self, input_dim = 40, num_classes=8)
models/x_vector_Indian_LID.py:17
Method__len__
(self)
SpeechDataGenerator.py:24
Method__len__
(self)
SpeechDataGenerator_precomp_feats.py:24
Functionfeature_extraction
(filepath,sr=16000, min_dur_sec=4,win_length=400,hop_length=160, n_mels=40, spec_len=400,mode='train')
utils/utils.py:31
Methodforward
input: size (batch, seq_len, input_features) outpu: size (batch, new_seq_len, output_features)
models/tdnn.py:53
Methodforward
(self, inputs)
models/x_vector.py:29
Methodforward
(self, inputs)
models/x_vector_Indian_LID.py:29
Functionlin_mel_from_wav
(wav, hop_length, win_length, n_mels)
utils/utils.py:22
Functionload_data
(filepath,sr=16000, min_dur_sec=4,win_length=400,hop_length=160, n_mels=40, spec_len=400,mode='train')
utils/utils.py:43
Functionload_npy_data
(filepath,spec_len=400,mode='train')
utils/utils.py:63
Functionspeech_collate
(batch)
utils/utils.py:76