MCPcopy Create free account

hub / github.com/calclavia/tal-asrd / types & classes

Types & classes35 in github.com/calclavia/tal-asrd

↓ 6 callersClassASRAlignedDataset
Audio -> Text dataset. Provides well aligned audio utterances. Two special tokens are used. Text format: Begin episode
tal/asr/data/aligned.py:76
↓ 5 callersClassASRAlignedCollater
Collates data
tal/asr/data/aligned.py:240
↓ 4 callersClassSystem
tal/asr/system.py:26
↓ 3 callersClassTokenizer
tal/asr/tokenizers/sentencepiece.py:17
↓ 3 callersClassWandbLoggerWrapper
tal/asr/logger.py:5
↓ 2 callersClassBeamState
Structure that contains necessary states for beam search.
tal/diarization/uisrnn/uisrnn.py:42
↓ 2 callersClassLabelSmoothLoss
tal/asr/util.py:19
↓ 2 callersClassLamb
r""" https://github.com/cybertronai/pytorch-lamb Implements Lamb algorithm. It has been proposed in `Large Batch Optimization for Deep Lea
tal/optimizers.py:302
↓ 2 callersClassLogMelSpec
Performs log melspec transformation on raw audio Adapted from https://github.com/zcaceres/spec_augment/blob/master/SpecAugment.ipynb P
tal/asr/models.py:15
↓ 2 callersClassModRZTXDecoderLayer
Modified version of decoder layer that caches the attention weights for analysis
tal/asr/models.py:488
↓ 2 callersClassSDUtteranceCollater
Collates data
tal/asr/data/baseline_speaker.py:214
↓ 2 callersClassSDUtteranceDataset
Audio -> Text dataset. Provides well aligned audio utterances. Two special tokens are used. Text format: Begin episode <EOS>
tal/asr/data/baseline_speaker.py:75
↓ 2 callersClassSystem
tal/baseline/speaker_system.py:25
↓ 2 callersClassTDS
Acoustic model
tal/asr/models.py:349
↓ 1 callersClassASRModel
tal/asr/models.py:56
↓ 1 callersClassASRSegmentDataset
Audio -> Text dataset. During training we obtain a random segment of audio and ask the model to predict all utterances within that c
tal/asr/data/segment.py:56
↓ 1 callersClassCoreRNN
The core Recurent Neural Network used by UIS-RNN.
tal/diarization/uisrnn/uisrnn.py:20
↓ 1 callersClassDefaultArgs
tal/asr/transcribe.py:213
↓ 1 callersClassFrame
Represents a "frame" of audio data.
tal/asr/speech_detect.py:36
↓ 1 callersClassFrame
Represents a "frame" of audio data.
tal/vad/webrtcvad.py:49
↓ 1 callersClassPositionalEncoding
r"""Inject some information about the relative or absolute position of the tokens in the sequence. The positional encodings have the same dim
tal/modules.py:24
↓ 1 callersClassSDModel
tal/asr/models.py:400
↓ 1 callersClassSuppressPrint
tal/__init__.py:43
↓ 1 callersClassSystem
tal/asr/train_embed.py:21
↓ 1 callersClassTDSBlock
tal/asr/models.py:298
ClassASRSegmentCollater
Collates data
tal/asr/data/segment.py:304
ClassAdafactor
Fairseq implementation Implements Adafactor algorithm. https://github.com/pytorch/fairseq/blob/master/fairseq/optim/adafactor.py This
tal/optimizers.py:84
ClassAudioCollator
Collates data
tal/asr/data/audio.py:107
ClassLogger
A class for printing logging information to screen.
tal/diarization/uisrnn/utils.py:15
ClassLookahead
tal/optimizers.py:234
ClassRAdam
tal/optimizers.py:9
ClassRandomSegmentDataset
A dataset that produces random audio segments from a directory
tal/asr/data/audio.py:29
ClassTokenizer
tal/asr/tokenizers/transformers.py:11
ClassUISRNN
Unbounded Interleaved-State Recurrent Neural Networks.
tal/diarization/uisrnn/uisrnn.py:67
Class_Tokenizer
tal/asr/tokenizers/__init__.py:7