torchaudio

GPTKB entity

Statements (54)
Predicate Object
gptkbp:instanceOf gptkb:software
gptkbp:compatibleWith gptkb:PyTorch
gptkbp:developedBy gptkb:PyTorch_Team
gptkbp:documentation https://pytorch.org/audio/stable/index.html
gptkbp:firstReleased 2019
https://www.w3.org/2000/01/rdf-schema#label torchaudio
gptkbp:latestReleaseVersion 2.2.0
gptkbp:license gptkb:BSD-3-Clause
gptkbp:npmPackage gptkb:torchaudio
gptkbp:partOf gptkb:PyTorch_Ecosystem
gptkbp:programmingLanguage gptkb:Python
gptkbp:provides gptkb:MFCC
gptkb:MelSpectrogram
gptkb:pre-trained_ConvTasNet_models
gptkb:pre-trained_DeepSpeech_models
gptkb:pre-trained_Emformer_models
gptkb:pre-trained_HuBERT_models
gptkb:pre-trained_WavLM_models
gptkb:pre-trained_WaveRNN_models
gptkb:pre-trained_wav2vec2_models
gptkb:Spectrogram
gptkb:VAD
pre-trained models
I/O utilities
Kaldi compatibility
Resample
audio transforms
compliance module
datasets module
functional module
models module
pipelines module
pre-trained RNNT models
pre-trained Tacotron2 models
pre-trained audio classification models
pre-trained source separation models
pre-trained speech enhancement models
pre-trained speech recognition models
pre-trained wavernn vocoder
sox effects
gptkbp:repository https://github.com/pytorch/audio
gptkbp:supports deep learning
speech recognition
audio processing
audio datasets
gptkbp:usedFor data augmentation
machine learning research
speech-to-text
audio classification
audio feature extraction
source separation
speech enhancement
gptkbp:bfsParent gptkb:PyTorch
gptkbp:bfsLayer 5