All modules for which code is available
- torchaudio._backend
- torchaudio._torchcodec
- torchaudio.compliance.kaldi
- torchaudio.datasets.cmuarctic
- torchaudio.datasets.cmudict
- torchaudio.datasets.commonvoice
- torchaudio.datasets.dr_vctk
- torchaudio.datasets.fluentcommands
- torchaudio.datasets.gtzan
- torchaudio.datasets.iemocap
- torchaudio.datasets.librilight_limited
- torchaudio.datasets.librimix
- torchaudio.datasets.librispeech
- torchaudio.datasets.libritts
- torchaudio.datasets.ljspeech
- torchaudio.datasets.musdb_hq
- torchaudio.datasets.quesst14
- torchaudio.datasets.snips
- torchaudio.datasets.speechcommands
- torchaudio.datasets.tedlium
- torchaudio.datasets.vctk
- torchaudio.datasets.voxceleb1
- torchaudio.datasets.yesno
- torchaudio.functional._alignment
- torchaudio.functional.filtering
- torchaudio.functional.functional
- torchaudio.io._effector
- torchaudio.io._playback
- torchaudio.kaldi_io
- torchaudio.models._hdemucs
- torchaudio.models.conformer
- torchaudio.models.conv_tasnet
- torchaudio.models.decoder._ctc_decoder
- torchaudio.models.decoder._cuda_ctc_decoder
- torchaudio.models.deepspeech
- torchaudio.models.emformer
- torchaudio.models.rnnt
- torchaudio.models.rnnt_decoder
- torchaudio.models.squim.objective
- torchaudio.models.squim.subjective
- torchaudio.models.tacotron2
- torchaudio.models.wav2letter
- torchaudio.models.wav2vec2.model
- torchaudio.models.wav2vec2.utils.import_fairseq
- torchaudio.models.wav2vec2.utils.import_huggingface
- torchaudio.models.wavernn
- torchaudio.pipelines._source_separation_pipeline
- torchaudio.pipelines._squim_pipeline
- torchaudio.pipelines._tts.interface
- torchaudio.pipelines._wav2vec2.impl
- torchaudio.pipelines.rnnt_pipeline
- torchaudio.prototype.datasets.musan
- torchaudio.prototype.functional._dsp
- torchaudio.prototype.functional._rir
- torchaudio.prototype.functional.functional
- torchaudio.prototype.models._conformer_wav2vec2
- torchaudio.prototype.models._emformer_hubert
- torchaudio.prototype.models.conv_emformer
- torchaudio.prototype.models.hifi_gan
- torchaudio.prototype.models.rnnt
- torchaudio.prototype.pipelines._vggish._vggish_pipeline
- torchaudio.prototype.pipelines.hifigan_pipeline
- torchaudio.prototype.transforms._transforms
- torchaudio.sox_effects.sox_effects
- torchaudio.transforms._multi_channel
- torchaudio.transforms._transforms
- torchaudio.utils.sox_utils
- torio.io._streaming_media_decoder
- torio.io._streaming_media_encoder
- torio.utils.ffmpeg_utils
