torchaudio Documentation

Attributes

• torchaudio.functional.TokenSpan.end
• torchaudio.functional.TokenSpan.score
• torchaudio.functional.TokenSpan.start
• torchaudio.functional.TokenSpan.token
• torchaudio.io.StreamReader
• torchaudio.io.StreamWriter
• torchaudio.models.decoder.CTCHypothesis.score
• torchaudio.models.decoder.CTCHypothesis.timesteps
• torchaudio.models.decoder.CTCHypothesis.tokens
• torchaudio.models.decoder.CTCHypothesis.words
• torchaudio.models.decoder.CUCTCHypothesis.score
• torchaudio.models.decoder.CUCTCHypothesis.tokens
• torchaudio.models.decoder.CUCTCHypothesis.words
• torio.io.CodecConfig.bit_rate
• torio.io.CodecConfig.compression_level
• torio.io.CodecConfig.gop_size
• torio.io.CodecConfig.max_b_frames
• torio.io.CodecConfig.qscale
• torio.io._streaming_media_decoder.ChunkTensor.pts
• torio.io._streaming_media_decoder.OutputAudioStream.num_channels
• torio.io._streaming_media_decoder.OutputAudioStream.sample_rate
• torio.io._streaming_media_decoder.OutputStream.filter_description
• torio.io._streaming_media_decoder.OutputStream.format
• torio.io._streaming_media_decoder.OutputStream.media_type
• torio.io._streaming_media_decoder.OutputStream.source_index
• torio.io._streaming_media_decoder.OutputVideoStream.frame_rate
• torio.io._streaming_media_decoder.OutputVideoStream.height
• torio.io._streaming_media_decoder.OutputVideoStream.width
• torio.io._streaming_media_decoder.SourceAudioStream.num_channels
• torio.io._streaming_media_decoder.SourceAudioStream.sample_rate
• torio.io._streaming_media_decoder.SourceStream.bit_rate
• torio.io._streaming_media_decoder.SourceStream.bits_per_sample
• torio.io._streaming_media_decoder.SourceStream.codec
• torio.io._streaming_media_decoder.SourceStream.codec_long_name
• torio.io._streaming_media_decoder.SourceStream.format
• torio.io._streaming_media_decoder.SourceStream.media_type
• torio.io._streaming_media_decoder.SourceStream.metadata
• torio.io._streaming_media_decoder.SourceStream.num_frames
• torio.io._streaming_media_decoder.SourceVideoStream.frame_rate
• torio.io._streaming_media_decoder.SourceVideoStream.height
• torio.io._streaming_media_decoder.SourceVideoStream.width
• torio::io::Chunk::frames
• torio::io::Chunk::pts
• torio::io::OutputStreamInfo::filter_description
• torio::io::OutputStreamInfo::format
• torio::io::OutputStreamInfo::frame_rate
• torio::io::OutputStreamInfo::height
• torio::io::OutputStreamInfo::media_type
• torio::io::OutputStreamInfo::num_channels
• torio::io::OutputStreamInfo::sample_rate
• torio::io::OutputStreamInfo::source_index
• torio::io::OutputStreamInfo::width
• torio::io::SrcStreamInfo::bit_rate
• torio::io::SrcStreamInfo::bits_per_sample
• torio::io::SrcStreamInfo::codec_long_name
• torio::io::SrcStreamInfo::codec_name
• torio::io::SrcStreamInfo::fmt_name
• torio::io::SrcStreamInfo::frame_rate
• torio::io::SrcStreamInfo::height
• torio::io::SrcStreamInfo::media_type
• torio::io::SrcStreamInfo::metadata
• torio::io::SrcStreamInfo::num_channels
• torio::io::SrcStreamInfo::num_frames
• torio::io::SrcStreamInfo::sample_rate
• torio::io::SrcStreamInfo::width

Classs

• torchaudio.AudioMetaData
• torchaudio.datasets.CMUARCTIC
• torchaudio.datasets.CMUDict
• torchaudio.datasets.COMMONVOICE
• torchaudio.datasets.DR_VCTK
• torchaudio.datasets.FluentSpeechCommands
• torchaudio.datasets.GTZAN
• torchaudio.datasets.IEMOCAP
• torchaudio.datasets.LIBRISPEECH
• torchaudio.datasets.LIBRITTS
• torchaudio.datasets.LJSPEECH
• torchaudio.datasets.LibriLightLimited
• torchaudio.datasets.LibriMix
• torchaudio.datasets.MUSDB_HQ
• torchaudio.datasets.QUESST14
• torchaudio.datasets.SPEECHCOMMANDS
• torchaudio.datasets.Snips
• torchaudio.datasets.TEDLIUM
• torchaudio.datasets.VCTK_092
• torchaudio.datasets.VoxCeleb1Identification
• torchaudio.datasets.VoxCeleb1Verification
• torchaudio.datasets.YESNO
• torchaudio.functional.TokenSpan
• torchaudio.io.AudioEffector
• torchaudio.io._playback.play_audio
• torchaudio.models.Conformer
• torchaudio.models.ConvTasNet
• torchaudio.models.DeepSpeech
• torchaudio.models.Emformer
• torchaudio.models.HDemucs
• torchaudio.models.HuBERTPretrainModel
• torchaudio.models.RNNT
• torchaudio.models.RNNTBeamSearch
• torchaudio.models.SquimObjective
• torchaudio.models.SquimSubjective
• torchaudio.models.Tacotron2
• torchaudio.models.Wav2Letter
• torchaudio.models.Wav2Vec2Model
• torchaudio.models.WaveRNN
• torchaudio.models.decoder.CTCDecoder
• torchaudio.models.decoder.CTCDecoderLM
• torchaudio.models.decoder.CTCDecoderLMState
• torchaudio.models.decoder.CTCHypothesis
• torchaudio.models.decoder.CUCTCDecoder
• torchaudio.models.decoder.CUCTCHypothesis
• torchaudio.pipelines.RNNTBundle
• torchaudio.pipelines.RNNTBundle.FeatureExtractor
• torchaudio.pipelines.RNNTBundle.TokenProcessor
• torchaudio.pipelines.SourceSeparationBundle
• torchaudio.pipelines.SquimObjectiveBundle
• torchaudio.pipelines.SquimSubjectiveBundle
• torchaudio.pipelines.Tacotron2TTSBundle
• torchaudio.pipelines.Tacotron2TTSBundle.TextProcessor
• torchaudio.pipelines.Tacotron2TTSBundle.Vocoder
• torchaudio.pipelines.Wav2Vec2ASRBundle
• torchaudio.pipelines.Wav2Vec2Bundle
• torchaudio.pipelines.Wav2Vec2FABundle
• torchaudio.pipelines.Wav2Vec2FABundle.Aligner
• torchaudio.pipelines.Wav2Vec2FABundle.Tokenizer
• torchaudio.prototype.datasets.Musan
• torchaudio.prototype.models.ConformerWav2Vec2PretrainModel
• torchaudio.prototype.models.ConvEmformer
• torchaudio.prototype.models.HiFiGANVocoder
• torchaudio.prototype.pipelines.HiFiGANVocoderBundle
• torchaudio.prototype.pipelines.VGGishBundle
• torchaudio.prototype.pipelines.VGGishBundle.VGGish
• torchaudio.prototype.pipelines.VGGishBundle.VGGishInputProcessor
• torchaudio.prototype.transforms.BarkScale
• torchaudio.prototype.transforms.BarkSpectrogram
• torchaudio.prototype.transforms.ChromaScale
• torchaudio.prototype.transforms.ChromaSpectrogram
• torchaudio.prototype.transforms.InverseBarkScale
• torchaudio.transforms.AddNoise
• torchaudio.transforms.AmplitudeToDB
• torchaudio.transforms.ComputeDeltas
• torchaudio.transforms.Convolve
• torchaudio.transforms.Deemphasis
• torchaudio.transforms.FFTConvolve
• torchaudio.transforms.Fade
• torchaudio.transforms.FrequencyMasking
• torchaudio.transforms.GriffinLim
• torchaudio.transforms.InverseMelScale
• torchaudio.transforms.InverseSpectrogram
• torchaudio.transforms.LFCC
• torchaudio.transforms.Loudness
• torchaudio.transforms.MFCC
• torchaudio.transforms.MVDR
• torchaudio.transforms.MelScale
• torchaudio.transforms.MelSpectrogram
• torchaudio.transforms.MuLawDecoding
• torchaudio.transforms.MuLawEncoding
• torchaudio.transforms.PSD
• torchaudio.transforms.PitchShift
• torchaudio.transforms.Preemphasis
• torchaudio.transforms.RNNTLoss
• torchaudio.transforms.RTFMVDR
• torchaudio.transforms.Resample
• torchaudio.transforms.SlidingWindowCmn
• torchaudio.transforms.SoudenMVDR
• torchaudio.transforms.SpectralCentroid
• torchaudio.transforms.Spectrogram
• torchaudio.transforms.Speed
• torchaudio.transforms.SpeedPerturbation
• torchaudio.transforms.TimeMasking
• torchaudio.transforms.TimeStretch
• torchaudio.transforms.Vad
• torchaudio.transforms.Vol
• torio.io.CodecConfig
• torio.io.StreamingMediaDecoder
• torio.io.StreamingMediaEncoder
• torio.io._streaming_media_decoder.ChunkTensor
• torio.io._streaming_media_decoder.OutputAudioStream
• torio.io._streaming_media_decoder.OutputStream
• torio.io._streaming_media_decoder.OutputVideoStream
• torio.io._streaming_media_decoder.SourceAudioStream
• torio.io._streaming_media_decoder.SourceStream
• torio.io._streaming_media_decoder.SourceVideoStream
• torio::io::Chunk
• torio::io::OutputStreamInfo
• torio::io::SrcStreamInfo
• torio::io::StreamingMediaDecoder
• torio::io::StreamingMediaDecoderCustomIO
• torio::io::StreamingMediaEncoder
• torio::io::StreamingMediaEncoderCustomIO

Functions

• torchaudio.compliance.kaldi.fbank
• torchaudio.compliance.kaldi.mfcc
• torchaudio.compliance.kaldi.spectrogram
• torchaudio.functional.DB_to_amplitude
• torchaudio.functional.add_noise
• torchaudio.functional.allpass_biquad
• torchaudio.functional.amplitude_to_DB
• torchaudio.functional.apply_beamforming
• torchaudio.functional.apply_codec
• torchaudio.functional.band_biquad
• torchaudio.functional.bandpass_biquad
• torchaudio.functional.bandreject_biquad
• torchaudio.functional.bass_biquad
• torchaudio.functional.biquad
• torchaudio.functional.compute_deltas
• torchaudio.functional.contrast
• torchaudio.functional.convolve
• torchaudio.functional.create_dct
• torchaudio.functional.dcshift
• torchaudio.functional.deemph_biquad
• torchaudio.functional.deemphasis
• torchaudio.functional.detect_pitch_frequency
• torchaudio.functional.dither
• torchaudio.functional.edit_distance
• torchaudio.functional.equalizer_biquad
• torchaudio.functional.fftconvolve
• torchaudio.functional.filtfilt
• torchaudio.functional.flanger
• torchaudio.functional.forced_align
• torchaudio.functional.frechet_distance
• torchaudio.functional.gain
• torchaudio.functional.griffinlim
• torchaudio.functional.highpass_biquad
• torchaudio.functional.inverse_spectrogram
• torchaudio.functional.lfilter
• torchaudio.functional.linear_fbanks
• torchaudio.functional.loudness
• torchaudio.functional.lowpass_biquad
• torchaudio.functional.mask_along_axis
• torchaudio.functional.mask_along_axis_iid
• torchaudio.functional.melscale_fbanks
• torchaudio.functional.merge_tokens
• torchaudio.functional.mu_law_decoding
• torchaudio.functional.mu_law_encoding
• torchaudio.functional.mvdr_weights_rtf
• torchaudio.functional.mvdr_weights_souden
• torchaudio.functional.overdrive
• torchaudio.functional.phase_vocoder
• torchaudio.functional.phaser
• torchaudio.functional.pitch_shift
• torchaudio.functional.preemphasis
• torchaudio.functional.psd
• torchaudio.functional.resample
• torchaudio.functional.riaa_biquad
• torchaudio.functional.rnnt_loss
• torchaudio.functional.rtf_evd
• torchaudio.functional.rtf_power
• torchaudio.functional.sliding_window_cmn
• torchaudio.functional.spectral_centroid
• torchaudio.functional.spectrogram
• torchaudio.functional.speed
• torchaudio.functional.treble_biquad
• torchaudio.functional.vad
• torchaudio.info
• torchaudio.kaldi_io.read_mat_ark
• torchaudio.kaldi_io.read_mat_scp
• torchaudio.kaldi_io.read_vec_flt_ark
• torchaudio.kaldi_io.read_vec_flt_scp
• torchaudio.kaldi_io.read_vec_int_ark
• torchaudio.list_audio_backends
• torchaudio.load
• torchaudio.models.conv_tasnet_base
• torchaudio.models.decoder.ctc_decoder
• torchaudio.models.decoder.cuda_ctc_decoder
• torchaudio.models.decoder.download_pretrained_files
• torchaudio.models.emformer_rnnt_base
• torchaudio.models.emformer_rnnt_model
• torchaudio.models.hdemucs_high
• torchaudio.models.hdemucs_low
• torchaudio.models.hdemucs_medium
• torchaudio.models.hubert_base
• torchaudio.models.hubert_large
• torchaudio.models.hubert_pretrain_base
• torchaudio.models.hubert_pretrain_large
• torchaudio.models.hubert_pretrain_model
• torchaudio.models.hubert_pretrain_xlarge
• torchaudio.models.hubert_xlarge
• torchaudio.models.squim_objective_base
• torchaudio.models.squim_objective_model
• torchaudio.models.squim_subjective_base
• torchaudio.models.squim_subjective_model
• torchaudio.models.wav2vec2.utils.import_fairseq_model
• torchaudio.models.wav2vec2.utils.import_huggingface_model
• torchaudio.models.wav2vec2_base
• torchaudio.models.wav2vec2_large
• torchaudio.models.wav2vec2_large_lv60k
• torchaudio.models.wav2vec2_model
• torchaudio.models.wav2vec2_xlsr_1b
• torchaudio.models.wav2vec2_xlsr_2b
• torchaudio.models.wav2vec2_xlsr_300m
• torchaudio.models.wavlm_base
• torchaudio.models.wavlm_large
• torchaudio.models.wavlm_model
• torchaudio.prototype.functional.adsr_envelope
• torchaudio.prototype.functional.barkscale_fbanks
• torchaudio.prototype.functional.chroma_filterbank
• torchaudio.prototype.functional.extend_pitch
• torchaudio.prototype.functional.filter_waveform
• torchaudio.prototype.functional.frequency_impulse_response
• torchaudio.prototype.functional.oscillator_bank
• torchaudio.prototype.functional.ray_tracing
• torchaudio.prototype.functional.simulate_rir_ism
• torchaudio.prototype.functional.sinc_impulse_response
• torchaudio.prototype.models.conformer_rnnt_base
• torchaudio.prototype.models.conformer_rnnt_model
• torchaudio.prototype.models.conformer_wav2vec2_base
• torchaudio.prototype.models.conformer_wav2vec2_model
• torchaudio.prototype.models.conformer_wav2vec2_pretrain_base
• torchaudio.prototype.models.conformer_wav2vec2_pretrain_large
• torchaudio.prototype.models.conformer_wav2vec2_pretrain_model
• torchaudio.prototype.models.emformer_hubert_base
• torchaudio.prototype.models.emformer_hubert_model
• torchaudio.prototype.models.hifigan_vocoder
• torchaudio.prototype.models.hifigan_vocoder_v1
• torchaudio.prototype.models.hifigan_vocoder_v2
• torchaudio.prototype.models.hifigan_vocoder_v3
• torchaudio.save
• torchaudio.sox_effects.apply_effects_file
• torchaudio.sox_effects.apply_effects_tensor
• torchaudio.sox_effects.effect_names
• torchaudio.utils.ffmpeg_utils.clear_cuda_context_cache
• torchaudio.utils.ffmpeg_utils.get_audio_decoders
• torchaudio.utils.ffmpeg_utils.get_audio_encoders
• torchaudio.utils.ffmpeg_utils.get_build_config
• torchaudio.utils.ffmpeg_utils.get_demuxers
• torchaudio.utils.ffmpeg_utils.get_input_devices
• torchaudio.utils.ffmpeg_utils.get_input_protocols
• torchaudio.utils.ffmpeg_utils.get_log_level
• torchaudio.utils.ffmpeg_utils.get_muxers
• torchaudio.utils.ffmpeg_utils.get_output_devices
• torchaudio.utils.ffmpeg_utils.get_output_protocols
• torchaudio.utils.ffmpeg_utils.get_versions
• torchaudio.utils.ffmpeg_utils.get_video_decoders
• torchaudio.utils.ffmpeg_utils.get_video_encoders
• torchaudio.utils.ffmpeg_utils.set_log_level
• torchaudio.utils.sox_utils.get_buffer_size
• torchaudio.utils.sox_utils.list_effects
• torchaudio.utils.sox_utils.list_read_formats
• torchaudio.utils.sox_utils.list_write_formats
• torchaudio.utils.sox_utils.set_buffer_size
• torchaudio.utils.sox_utils.set_seed
• torchaudio.utils.sox_utils.set_use_threads
• torchaudio.utils.sox_utils.set_verbosity
• torio.utils.ffmpeg_utils.clear_cuda_context_cache
• torio.utils.ffmpeg_utils.get_audio_decoders
• torio.utils.ffmpeg_utils.get_audio_encoders
• torio.utils.ffmpeg_utils.get_build_config
• torio.utils.ffmpeg_utils.get_demuxers
• torio.utils.ffmpeg_utils.get_input_devices
• torio.utils.ffmpeg_utils.get_input_protocols
• torio.utils.ffmpeg_utils.get_log_level
• torio.utils.ffmpeg_utils.get_muxers
• torio.utils.ffmpeg_utils.get_output_devices
• torio.utils.ffmpeg_utils.get_output_protocols
• torio.utils.ffmpeg_utils.get_versions
• torio.utils.ffmpeg_utils.get_video_decoders
• torio.utils.ffmpeg_utils.get_video_encoders
• torio.utils.ffmpeg_utils.set_log_level
• torio::io::StreamingMediaDecoder::add_audio_stream
• torio::io::StreamingMediaDecoder::add_video_stream
• torio::io::StreamingMediaDecoder::fill_buffer
• torio::io::StreamingMediaDecoder::find_best_audio_stream
• torio::io::StreamingMediaDecoder::find_best_video_stream
• torio::io::StreamingMediaDecoder::get_metadata
• torio::io::StreamingMediaDecoder::get_out_stream_info
• torio::io::StreamingMediaDecoder::get_src_stream_info
• torio::io::StreamingMediaDecoder::is_buffer_ready
• torio::io::StreamingMediaDecoder::num_out_streams
• torio::io::StreamingMediaDecoder::num_src_streams
• torio::io::StreamingMediaDecoder::pop_chunks
• torio::io::StreamingMediaDecoder::process_all_packets
• torio::io::StreamingMediaDecoder::process_packet
• torio::io::StreamingMediaDecoder::process_packet_block
• torio::io::StreamingMediaDecoder::remove_stream
• torio::io::StreamingMediaDecoder::seek
• torio::io::StreamingMediaDecoderCustomIO::StreamingMediaDecoderCustomIO
• torio::io::StreamingMediaEncoder::StreamingMediaEncoder
• torio::io::StreamingMediaEncoder::add_audio_stream
• torio::io::StreamingMediaEncoder::add_video_stream
• torio::io::StreamingMediaEncoder::close
• torio::io::StreamingMediaEncoder::flush
• torio::io::StreamingMediaEncoder::open
• torio::io::StreamingMediaEncoder::set_metadata
• torio::io::StreamingMediaEncoder::write_audio_chunk
• torio::io::StreamingMediaEncoder::write_video_chunk
• torio::io::StreamingMediaEncoderCustomIO::StreamingMediaEncoderCustomIO

Guides

Methods

• torchaudio.datasets.CMUARCTIC.__getitem__
• torchaudio.datasets.CMUDict.__getitem__
• torchaudio.datasets.COMMONVOICE.__getitem__
• torchaudio.datasets.DR_VCTK.__getitem__
• torchaudio.datasets.FluentSpeechCommands.__getitem__
• torchaudio.datasets.FluentSpeechCommands.get_metadata
• torchaudio.datasets.GTZAN.__getitem__
• torchaudio.datasets.IEMOCAP.__getitem__
• torchaudio.datasets.IEMOCAP.get_metadata
• torchaudio.datasets.LIBRISPEECH.__getitem__
• torchaudio.datasets.LIBRISPEECH.get_metadata
• torchaudio.datasets.LIBRITTS.__getitem__
• torchaudio.datasets.LJSPEECH.__getitem__
• torchaudio.datasets.LibriLightLimited.__getitem__
• torchaudio.datasets.LibriMix.__getitem__
• torchaudio.datasets.LibriMix.get_metadata
• torchaudio.datasets.MUSDB_HQ.__getitem__
• torchaudio.datasets.QUESST14.__getitem__
• torchaudio.datasets.QUESST14.get_metadata
• torchaudio.datasets.SPEECHCOMMANDS.__getitem__
• torchaudio.datasets.SPEECHCOMMANDS.get_metadata
• torchaudio.datasets.Snips.__getitem__
• torchaudio.datasets.Snips.get_metadata
• torchaudio.datasets.TEDLIUM.__getitem__
• torchaudio.datasets.VCTK_092.__getitem__
• torchaudio.datasets.VoxCeleb1Identification.__getitem__
• torchaudio.datasets.VoxCeleb1Identification.get_metadata
• torchaudio.datasets.VoxCeleb1Verification.__getitem__
• torchaudio.datasets.VoxCeleb1Verification.get_metadata
• torchaudio.datasets.YESNO.__getitem__
• torchaudio.io.AudioEffector.apply
• torchaudio.io.AudioEffector.stream
• torchaudio.models.Conformer.forward
• torchaudio.models.ConvTasNet.forward
• torchaudio.models.DeepSpeech.forward
• torchaudio.models.Emformer.forward
• torchaudio.models.Emformer.infer
• torchaudio.models.HDemucs.forward
• torchaudio.models.HuBERTPretrainModel.forward
• torchaudio.models.RNNT.forward
• torchaudio.models.RNNT.join
• torchaudio.models.RNNT.predict
• torchaudio.models.RNNT.transcribe
• torchaudio.models.RNNT.transcribe_streaming
• torchaudio.models.RNNTBeamSearch.forward
• torchaudio.models.RNNTBeamSearch.infer
• torchaudio.models.SquimObjective.forward
• torchaudio.models.SquimSubjective.forward
• torchaudio.models.Tacotron2.forward
• torchaudio.models.Tacotron2.infer
• torchaudio.models.Wav2Letter.forward
• torchaudio.models.Wav2Vec2Model.extract_features
• torchaudio.models.Wav2Vec2Model.forward
• torchaudio.models.WaveRNN.forward
• torchaudio.models.WaveRNN.infer
• torchaudio.models.decoder.CTCDecoder.__call__
• torchaudio.models.decoder.CTCDecoder.decode_begin
• torchaudio.models.decoder.CTCDecoder.decode_end
• torchaudio.models.decoder.CTCDecoder.decode_step
• torchaudio.models.decoder.CTCDecoder.get_final_hypothesis
• torchaudio.models.decoder.CTCDecoder.idxs_to_tokens
• torchaudio.models.decoder.CTCDecoderLM.finish
• torchaudio.models.decoder.CTCDecoderLM.score
• torchaudio.models.decoder.CTCDecoderLM.start
• torchaudio.models.decoder.CTCDecoderLMState.child
• torchaudio.models.decoder.CTCDecoderLMState.compare
• torchaudio.models.decoder.CUCTCDecoder.__call__
• torchaudio.pipelines.RNNTBundle.FeatureExtractor.__call__
• torchaudio.pipelines.RNNTBundle.TokenProcessor.__call__
• torchaudio.pipelines.RNNTBundle.get_decoder
• torchaudio.pipelines.RNNTBundle.get_feature_extractor
• torchaudio.pipelines.RNNTBundle.get_streaming_feature_extractor
• torchaudio.pipelines.RNNTBundle.get_token_processor
• torchaudio.pipelines.SourceSeparationBundle.get_model
• torchaudio.pipelines.SquimObjectiveBundle.get_model
• torchaudio.pipelines.SquimSubjectiveBundle.get_model
• torchaudio.pipelines.Tacotron2TTSBundle.TextProcessor.__call__
• torchaudio.pipelines.Tacotron2TTSBundle.Vocoder.__call__
• torchaudio.pipelines.Tacotron2TTSBundle.get_tacotron2
• torchaudio.pipelines.Tacotron2TTSBundle.get_text_processor
• torchaudio.pipelines.Tacotron2TTSBundle.get_vocoder
• torchaudio.pipelines.Wav2Vec2ASRBundle.get_labels
• torchaudio.pipelines.Wav2Vec2ASRBundle.get_model
• torchaudio.pipelines.Wav2Vec2Bundle.get_model
• torchaudio.pipelines.Wav2Vec2FABundle.Aligner.__call__
• torchaudio.pipelines.Wav2Vec2FABundle.Tokenizer.__call__
• torchaudio.pipelines.Wav2Vec2FABundle.get_aligner
• torchaudio.pipelines.Wav2Vec2FABundle.get_dict
• torchaudio.pipelines.Wav2Vec2FABundle.get_labels
• torchaudio.pipelines.Wav2Vec2FABundle.get_model
• torchaudio.pipelines.Wav2Vec2FABundle.get_tokenizer
• torchaudio.prototype.datasets.Musan.__getitem__
• torchaudio.prototype.datasets.Musan.get_metadata
• torchaudio.prototype.models.ConformerWav2Vec2PretrainModel.forward
• torchaudio.prototype.models.ConvEmformer.forward
• torchaudio.prototype.models.ConvEmformer.infer
• torchaudio.prototype.models.HiFiGANVocoder.forward
• torchaudio.prototype.pipelines.HiFiGANVocoderBundle.get_mel_transform
• torchaudio.prototype.pipelines.HiFiGANVocoderBundle.get_vocoder
• torchaudio.prototype.pipelines.VGGishBundle.VGGish.forward
• torchaudio.prototype.pipelines.VGGishBundle.VGGishInputProcessor.__call__
• torchaudio.prototype.pipelines.VGGishBundle.get_input_processor
• torchaudio.prototype.pipelines.VGGishBundle.get_model
• torchaudio.prototype.transforms.BarkScale.forward
• torchaudio.prototype.transforms.BarkSpectrogram.forward
• torchaudio.prototype.transforms.ChromaScale.forward
• torchaudio.prototype.transforms.ChromaSpectrogram.forward
• torchaudio.prototype.transforms.InverseBarkScale.forward
• torchaudio.transforms.AddNoise.forward
• torchaudio.transforms.AmplitudeToDB.forward
• torchaudio.transforms.ComputeDeltas.forward
• torchaudio.transforms.Convolve.forward
• torchaudio.transforms.Deemphasis.forward
• torchaudio.transforms.FFTConvolve.forward
• torchaudio.transforms.Fade.forward
• torchaudio.transforms.GriffinLim.forward
• torchaudio.transforms.InverseMelScale.forward
• torchaudio.transforms.InverseSpectrogram.forward
• torchaudio.transforms.LFCC.forward
• torchaudio.transforms.Loudness.forward
• torchaudio.transforms.MFCC.forward
• torchaudio.transforms.MVDR.forward
• torchaudio.transforms.MelScale.forward
• torchaudio.transforms.MelSpectrogram.forward
• torchaudio.transforms.MuLawDecoding.forward
• torchaudio.transforms.MuLawEncoding.forward
• torchaudio.transforms.PSD.forward
• torchaudio.transforms.PitchShift.forward
• torchaudio.transforms.PitchShift.initialize_parameters
• torchaudio.transforms.Preemphasis.forward
• torchaudio.transforms.RNNTLoss.forward
• torchaudio.transforms.RTFMVDR.forward
• torchaudio.transforms.Resample.forward
• torchaudio.transforms.SlidingWindowCmn.forward
• torchaudio.transforms.SoudenMVDR.forward
• torchaudio.transforms.SpectralCentroid.forward
• torchaudio.transforms.Spectrogram.forward
• torchaudio.transforms.Speed.forward
• torchaudio.transforms.SpeedPerturbation.forward
• torchaudio.transforms.TimeStretch.forward
• torchaudio.transforms.Vad.forward
• torchaudio.transforms.Vol.forward
• torio.io.StreamingMediaDecoder.add_audio_stream
• torio.io.StreamingMediaDecoder.add_basic_audio_stream
• torio.io.StreamingMediaDecoder.add_basic_video_stream
• torio.io.StreamingMediaDecoder.add_video_stream
• torio.io.StreamingMediaDecoder.fill_buffer
• torio.io.StreamingMediaDecoder.get_metadata
• torio.io.StreamingMediaDecoder.get_out_stream_info
• torio.io.StreamingMediaDecoder.get_src_stream_info
• torio.io.StreamingMediaDecoder.is_buffer_ready
• torio.io.StreamingMediaDecoder.pop_chunks
• torio.io.StreamingMediaDecoder.process_all_packets
• torio.io.StreamingMediaDecoder.process_packet
• torio.io.StreamingMediaDecoder.remove_stream
• torio.io.StreamingMediaDecoder.seek
• torio.io.StreamingMediaDecoder.stream
• torio.io.StreamingMediaEncoder.add_audio_stream
• torio.io.StreamingMediaEncoder.add_video_stream
• torio.io.StreamingMediaEncoder.close
• torio.io.StreamingMediaEncoder.flush
• torio.io.StreamingMediaEncoder.open
• torio.io.StreamingMediaEncoder.set_metadata
• torio.io.StreamingMediaEncoder.write_audio_chunk
• torio.io.StreamingMediaEncoder.write_video_chunk

Modules

• torchaudio.compliance.kaldi
• torchaudio.datasets
• torchaudio.functional
• torchaudio.io
• torchaudio.kaldi_io
• torchaudio.models
• torchaudio.models.decoder
• torchaudio.pipelines
• torchaudio.prototype.datasets
• torchaudio.prototype.functional
• torchaudio.prototype.models
• torchaudio.prototype.pipelines
• torchaudio.prototype.transforms
• torchaudio.sox_effects
• torchaudio.transforms
• torchaudio.utils
• torchaudio.utils.ffmpeg_utils
• torchaudio.utils.sox_utils
• torio
• torio.io
• torio.utils
• torio.utils.ffmpeg_utils

Propertys

• torchaudio.datasets.CMUDict.symbols
• torchaudio.datasets.TEDLIUM.phoneme_dict
• torchaudio.models.decoder.CTCDecoderLMState.children
• torchaudio.pipelines.RNNTBundle.hop_length
• torchaudio.pipelines.RNNTBundle.n_fft
• torchaudio.pipelines.RNNTBundle.n_mels
• torchaudio.pipelines.RNNTBundle.right_context_length
• torchaudio.pipelines.RNNTBundle.sample_rate
• torchaudio.pipelines.RNNTBundle.segment_length
• torchaudio.pipelines.SourceSeparationBundle.sample_rate
• torchaudio.pipelines.SquimObjectiveBundle.sample_rate
• torchaudio.pipelines.SquimSubjectiveBundle.sample_rate
• torchaudio.pipelines.Tacotron2TTSBundle.TextProcessor.tokens
• torchaudio.pipelines.Tacotron2TTSBundle.Vocoder.sample_rate
• torchaudio.pipelines.Wav2Vec2ASRBundle.sample_rate
• torchaudio.pipelines.Wav2Vec2Bundle.sample_rate
• torchaudio.pipelines.Wav2Vec2FABundle.sample_rate
• torchaudio.prototype.pipelines.HiFiGANVocoderBundle.sample_rate
• torchaudio.prototype.pipelines.VGGishBundle.sample_rate
• torio.io.StreamingMediaDecoder.default_audio_stream
• torio.io.StreamingMediaDecoder.default_video_stream
• torio.io.StreamingMediaDecoder.num_out_streams
• torio.io.StreamingMediaDecoder.num_src_streams

Sections

• 1. Data acquisition
• 1. Install Conda and activate conda environment
• 1. Install JetPack
• 1. Install MSYS2
• 1. Install build tools
• 1. Install build tools
• 1. Overview
• 1. Overview
• 1. Overview
• 1. Overview
• 1. Overview
• 1080P
• 1080P
• 2. Checking the supported devices
• 2. Install PyTorch
• 2. Install dependencies
• 2. Launch MSYS2
• 2. Pre-processing
• 2. Preparation
• 2. Preparation
• 2. Preparation
• 2. Preparation
• 2. Start the dev environment
• 2. [Optional] Install jtop
• 2.1. Import the packages
• 2.2. Download audio data
• 2.3. Helper functions
• 3. Build TorchAudio
• 3. Building inference pipeline
• 3. Construct the pipeline
• 3. Construct the pipeline
• 3. Data acquisition
• 3. Generate Ideal Ratio Masks (IRMs)
• 3. Install PyTorch
• 3. Install build tools
• 3. Install build tools
• 3. Install pip in user env
• 3. Load Speech and Noise Sample
• 3.1. Load audio data
• 3.2. Compute STFT coefficients
• 3.2.1. Visualize mixture speech
• 3.2.2. Visualize clean speech
• 3.2.3. Visualize noise
• 3.3. Define the reference microphone
• 3.4. Compute IRMs
• 3.4.1. Visualize IRM of target speech
• 3.4.2. Visualize IRM of noise
• 360P
• 360P
• 4. Build FFmpeg
• 4. Building inference pipeline
• 4. Check the installation
• 4. Clone the torchaudio repository
• 4. Compute PSD matrices
• 4. Configure the application function
• 4. Configure the audio stream
• 4. Create distorted (noisy) speech samples
• 4. Install PyTorch
• 4. The main process
• 4. [Optional] cuDNN
• 5. Beamforming using SoudenMVDR
• 5. Build
• 5. Build TorchAudio
• 5. Install external dependencies
• 5. Run Model
• 5. Run stream inference
• 5. The main process
• 5. Verify the build
• 5. Visualize the waveforms
• 5.1 Separate Track
• 5.1. Apply beamforming
• 5.2 Audio Segmenting and Processing
• 5.2. Result for SoudenMVDR
• 5.3 Spectrograms and Audio
• 6. Beamforming using RTFMVDR
• 6. Build TorchAudio
• 6. Predict Objective Metrics
• 6.1. Compute RTF
• 6.2. Apply beamforming
• 6.3. Result for RTFMVDR with rtf_evd
• 6.4. Result for RTFMVDR with rtf_power
• 7. Predict Mean Opinion Scores (Subjective) Metric
• 720P
• 720P
• 8 bit mu-law
• 8. Comparison with ground truths and baselines
• ADSR Envelope
• ASR Inference with CTC Decoder
• ASR Inference with CTC Decoder
• ASR Inference with CTC Decoder
• ASR Inference with CUDA CTC Decoder
• ASR Inference with CUDA CTC Decoder
• ASR Inference with CUDA CTC Decoder
• Accelerated video decoding with NVDEC
• Accelerated video decoding with NVDEC
• Accelerated video decoding with NVDEC
• Accelerated video encoding with NVENC
• Accelerated video encoding with NVENC
• Accelerated video encoding with NVENC
• Acknowledgement
• Acknowledgement
• Acoustic Model and Set Up
• Acoustic Model and Set Up
• AddNoise
• AddNoise
• Adding background noise
• Additive Synthesis
• Additive Synthesis
• Additive Synthesis
• Advanced: Handling transcripts with <star> token
• Aligning transcripts to speech
• AmplitudeToDB
• AmplitudeToDB
• Applying codec to Tensor object
• Applying effects
• Applying effects and filtering
• Arbitrary frequence response
• Arbitrary shapes
• Audio / Video device input
• Audio Data Augmentation
• Audio Data Augmentation
• Audio Data Augmentation
• Audio Datasets
• Audio Datasets
• Audio Datasets
• Audio Examples
• Audio Examples
• Audio Feature Augmentation
• Audio Feature Augmentation
• Audio Feature Augmentation
• Audio Feature Extractions
• Audio Feature Extractions
• Audio Feature Extractions
• Audio I/O
• Audio I/O
• Audio I/O
• Audio Resampling
• Audio Resampling
• Audio Resampling
• Audio Samples
• Audio Samples
• Audio Stream
• Audio previews
• AudioEffector
• AudioEffector
• AudioEffector Usages
• AudioEffector Usages
• AudioEffector Usages
• AudioMetaData
• Augmentations
• Autograd
• Backend and Dispatcher
• Backend and Dispatcher
• Background noise
• Background noise added
• Band-pass filter
• BarkScale
• BarkScale
• BarkSpectrogram
• BarkSpectrogram
• Beam Search Decoder
• Beam Search Decoder Parameters
• Beam Search Decoder Parameters
• Bell sound
• Benchmark NVDEC with StreamReader
• Benchmark NVENC with StreamWriter
• Benchmark with flashlight CPU decoder
• Brick-wall filter
• Build FFmpeg with NVDEC/NVENC support
• Building from source
• Building from source
• Building on Jetson
• Building on Jetson
• Building on Linux and macOS
• Building on Linux and macOS
• Building on Windows
• Building on Windows
• CMUARCTIC
• CMUARCTIC
• CMUDict
• CMUDict
• COMMONVOICE
• COMMONVOICE
• CONVTASNET_BASE_LIBRI2MIX
• CONVTASNET_BASE_LIBRI2MIX
• CPU
• CTC Decoder
• CTC forced alignment API tutorial
• CTC forced alignment API tutorial
• CTC forced alignment API tutorial
• CTCDecoder
• CTCDecoder
• CTCDecoderLM
• CTCDecoderLMState
• CTCHypothesis
• CUCTCDecoder
• CUCTCDecoder
• CUCTCHypothesis
• CUDA
• CUDA CTC Decoder
• Cellular automaton
• Changing Frequencies across time
• Character-based encoding
• Check the GPU and CUDA version
• Check the prerequisites
• Check the prerequisites
• Checking the compute capability
• Checking the installation
• Checking the intallation
• Checking the source streams
• Checking the versions
• Chinese
• ChromaScale
• ChromaScale
• ChromaSpectrogram
• ChromaSpectrogram
• Chunk
• ChunkTensor
• Citing torchaudio
• Codec applied
• CodecConfig
• Codecs
• Combining multiple sine waves
• Comparing resizing methods
• Comparison against librosa
• Comparison against librosa
• Comparison against librosa
• Comparison against librosa
• Compatibility Matrix
• Computation times
• Computation times
• Computation times
• ComputeDeltas
• ComputeDeltas
• Computing alignments
• Conclusion
• Conclusion
• Conclusion
• Conclusion
• Conda
• Config methods
• Configure Methods
• Configuring ouptut streams
• Configuring output streams
• Configuring output streams
• Configuring output streams
• Conformer
• Conformer
• ConformerWav2Vec2PretrainModel
• ConformerWav2Vec2PretrainModel
• Construct CUDA Decoder
• Construct Decoders
• Constructors
• Constructors
• Controling resampling quality with parameters
• ConvEmformer
• ConvEmformer
• ConvTasNet
• ConvTasNet
• Convolve
• Convolve
• Creating a pipeline
• Creating multiple frequency pitches
• Creating the pipeline
• Custom Language Model
• Custom filters
• Customizing the build
• DR_VCTK
• DR_VCTK
• DSP
• Decode and resize
• Decode as CUDA frames
• Decoding videos with NVDEC
• Deemphasis
• Deemphasis
• DeepSpeech
• DeepSpeech
• Default streams
• Dependencies
• Device ASR with Emformer RNN-T
• Device ASR with Emformer RNN-T
• Device ASR with Emformer RNN-T
• Device AV-ASR with Emformer RNN-T
• Device AV-ASR with Emformer RNN-T
• Device AV-ASR with Emformer RNN-T
• Device Availability
• Devices
• Dispatcher Migration
• Dispatcher Migration
• Downloading Pretrained Files
• Downsample (16 -> 8 kHz)
• Downsample (48 -> 44.1 kHz)
• Drum Beats
• EMFORMER_RNNT_BASE_LIBRISPEECH
• EMFORMER_RNNT_BASE_LIBRISPEECH
• EMFORMER_RNNT_BASE_MUSTC
• EMFORMER_RNNT_BASE_MUSTC
• EMFORMER_RNNT_BASE_TEDLIUM3
• EMFORMER_RNNT_BASE_TEDLIUM3
• Edge detection
• Effects
• Effects applied
• Emformer
• Emformer
• Enabling GPU video decoder/encoder
• Enabling GPU video decoder/encoder
• Enabling GPU video decoder/encoder
• Encoding videos with NVENC
• Ex) Audio
• Ex) Image
• Ex) Video with audio
• Ex) Video without audio
• Example
• Example
• Example - Spectrum Visualizer
• Extracting acoustic features
• FFT filter - Robot 🤖
• FFT filter - Whisper
• FFTConvolve
• FFTConvolve
• Factory Functions
• Factory Functions
• Factory Functions
• Factory Functions
• Factory Functions
• Factory Functions
• Factory Functions
• Factory Functions
• Factory Functions
• Fade
• Fade
• Feature Classifications
• Feature Classifications
• Feature Extractions
• Feature Extractions
• Feature classification
• File-like objects
• File-like objects
• Files and Data for Decoder
• Files and Data for Decoder
• Filter design tutorial
• Filter design tutorial
• Filter design tutorial
• Filtered
• Filtered Noise
• Filtering
• Find the most likely path (backtracking)
• FluentSpeechCommands
• FluentSpeechCommands
• Forced Alignment
• Forced Alignment with Wav2Vec2
• Forced Alignment with Wav2Vec2
• Forced Alignment with Wav2Vec2
• Forced alignment for multilingual data
• Forced alignment for multilingual data
• Forced alignment for multilingual data
• Frame-level alignments
• Frequency Response
• Frequency Response
• Frequency Response
• Frequency Sampling
• FrequencyMasking
• FrequencyMasking
• Full Transcript
• G.722
• GTZAN
• GTZAN
• Gallery
• Generate alignment probability (trellis)
• Generate frame-wise label probability
• Generating emissions
• Generating transcripts
• German
• Greedy Decoder
• Griffin-Lim Vocoder
• GriffinLim
• GriffinLim
• GriffinLim
• HDEMUCS_HIGH_MUSDB
• HDEMUCS_HIGH_MUSDB
• HDEMUCS_HIGH_MUSDB_PLUS
• HDEMUCS_HIGH_MUSDB_PLUS
• HDemucs
• HDemucs
• HIFIGAN_VOCODER_V3_LJSPEECH
• HIFIGAN_VOCODER_V3_LJSPEECH
• HUBERT_ASR_LARGE
• HUBERT_ASR_LARGE
• HUBERT_ASR_XLARGE
• HUBERT_ASR_XLARGE
• HUBERT_BASE
• HUBERT_BASE
• HUBERT_LARGE
• HUBERT_LARGE
• HUBERT_XLARGE
• HUBERT_XLARGE
• HW resizing and cropping
• Harmonic Overtones
• Headerless media
• Helper Function
• Helper Function
• HiFiGAN Vocoder
• HiFiGANVocoder
• HiFiGANVocoder
• HiFiGANVocoderBundle
• HiFiGANVocoderBundle
• High-pass filter
• Highpass / lowpass filter
• Horizontal
• HuBERTPretrainModel
• HuBERTPretrainModel
• Hypothesis
• I/O
• IEMOCAP
• IEMOCAP
• Icon
• Impulse Response
• Impulse Response
• Impulse Response
• Inconsistent treatment of blank token
• Incremental decoding
• Index
• Inharmonic Paritials
• Install FFmpeg dependencies
• Install NVIDIA Video Codec Headers
• Installing pre-built binaries
• Installing pre-built binaries
• Interface
• Interface
• Interface
• Interface
• Interface
• Interface
• Interface
• Interface
• Interface
• Interface
• InverseBarkScale
• InverseBarkScale
• InverseMelScale
• InverseMelScale
• InverseSpectrogram
• InverseSpectrogram
• Italian
• John Conway's life game
• KenLM
• LFCC
• LFCC
• LFCC
• LIBRISPEECH
• LIBRISPEECH
• LIBRITTS
• LIBRITTS
• LJSPEECH
• LJSPEECH
• Language Model
• Lexicon
• LibriLightLimited
• LibriLightLimited
• LibriMix
• LibriMix
• Loading audio data
• Loading data
• Loading from file-like object
• Local files
• Local files
• Loss
• Loss
• Loudness
• Loudness
• Low-pass filter
• Lowpass filter width
• MFCC
• MFCC
• MFCC
• MMS_FA
• MMS_FA
• MPlayer Test patterns
• MSVC
• MUSDB_HQ
• MUSDB_HQ
• MVDR
• MVDR
• Mandelbrot
• Matrices
• Mel Filter Bank
• MelScale
• MelScale
• MelSpectrogram
• MelSpectrogram
• MelSpectrogram
• Merge the segments into words
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Methods
• Metric
• Mirror
• Module Index
• MuLawDecoding
• MuLawDecoding
• MuLawEncoding
• MuLawEncoding
• Multi-channel
• Multi-channel
• Musan
• Musan
• Music Source Separation with Hybrid Demucs
• Music Source Separation with Hybrid Demucs
• Music Source Separation with Hybrid Demucs
• Network protocols
• No Language Model
• Noise
• Normalizing the transcript
• Online ASR with Emformer RNN-T
• Online ASR with Emformer RNN-T
• Online ASR with Emformer RNN-T
• Opening the source
• Opening the source media
• Optional Dependencies
• Optional Dependencies
• Original
• Original
• Original
• Original
• Original
• Original
• Original speech
• Oscillating cutoff frequency
• Oscillator Bank
• Oscillator and ADSR envelope
• Oscillator and ADSR envelope
• Oscillator and ADSR envelope
• OutputAudioStream
• OutputStream
• OutputStreaminfo
• OutputVideoStream
• Overview
• Overview
• Overview
• Overview
• Overview
• Overview
• Overview
• Overview
• Overview
• Overview
• Overview
• Overview of audio features
• PSD
• PSD
• Partial Transcript with <star> token
• Partial Transcript without <star> token
• Performance Benchmarking
• Pertrained Models
• Phoneme-based encoding
• Pitch
• PitchShift
• PitchShift
• Pixel manipulation
• Playing Video
• Playing audio
• Pluck
• Polish
• Portuguese
• Preemphasis
• Preemphasis
• Preparation
• Preparation
• Preparation
• Preparation
• Preparation
• Preparation
• Preparation
• Preparation
• Preparation
• Preparation
• Preparation
• Preparation
• Prepare Canvas
• Prepare Data
• Pretrained Models
• Pretrained Models
• Pretrained Models
• Pretrained Models
• Pretrained Models
• Pretrained Models
• Pretrained Models
• Pretrained Models
• Pretrained Models
• Pretrained Models
• Properties
• Properties
• Properties
• Properties
• Properties
• Properties
• Properties
• Properties
• Properties
• Properties
• Properties
• Properties
• Properties
• Properties
• Properties
• Prototype Factory Functions
• Prototype Factory Functions
• Prototype Factory Functions of Beta Models
• QUESST14
• QUESST14
• QVGA
• QVGA
• Quality Spotcheck
• Query Methods
• Querying audio metadata
• Querying file-like object
• RIR applied
• RIR applied
• RNN-T Streaming/Non-Streaming ASR
• RNN-T Streaming/Non-Streaming ASR
• RNN-T Streaming/Non-Streaming ASR
• RNNT
• RNNT
• RNNTBeamSearch
• RNNTBeamSearch
• RNNTBundle
• RNNTBundle
• RNNTBundle.FeatureExtractor
• RNNTBundle.FeatureExtractor
• RNNTBundle.TokenProcessor
• RNNTBundle.TokenProcessor
• RNNTLoss
• RNNTLoss
• RTFMVDR
• RTFMVDR
• RTMP (Real-Time Messaging Protocol)
• Random rotation
• References
• References
• References
• References
• References
• References
• Resample
• Resample
• Resampling Overview
• Result
• Result
• Result
• Result
• Retrieval Methods
• Riser
• Rolloff
• Room Impulse Response Simulation
• Run Inference
• Run Inference
• SNR 10 dB
• SNR 20 dB
• SNR 3 dB
• SPEECHCOMMANDS
• SPEECHCOMMANDS
• SQUIM_OBJECTIVE
• SQUIM_OBJECTIVE
• SQUIM_SUBJECTIVE
• SQUIM_SUBJECTIVE
• Saving audio to file
• Saving to file-like object
• Sawtooth wave
• Search Page
• Segment the path
• Sierpinski carpet/triangle fractal
• Signal with arbitral expression
• Simple Sine Wave
• Simulating a phone recoding
• Simulating room reverberation
• Sine wave
• SlidingWindowCmn
• SlidingWindowCmn
• Snips
• Snips
• SoudenMVDR
• SoudenMVDR
• Source Separation
• SourceAudioStream
• SourceSeparationBundle
• SourceSeparationBundle
• SourceStream
• SourceVideoStream
• SpecAugment
• SpectralCentroid
• SpectralCentroid
• Spectrogram
• Spectrogram
• Spectrogram
• Spectrogram Generation
• Speech Enhancement with MVDR Beamforming
• Speech Enhancement with MVDR Beamforming
• Speech Enhancement with MVDR Beamforming
• Speech Recognition with Wav2Vec2
• Speech Recognition with Wav2Vec2
• Speech Recognition with Wav2Vec2
• Speed
• Speed
• SpeedPerturbation
• SpeedPerturbation
• Square wave
• Squim Objective
• Squim Subjective
• SquimObjective
• SquimObjective
• SquimObjectiveBundle
• SquimObjectiveBundle
• SquimSubjective
• SquimSubjective
• SquimSubjectiveBundle
• SquimSubjectiveBundle
• SrcStreaminfo
• Stream Methods
• StreamReader
• StreamReader
• StreamReader Advanced Usages
• StreamReader Advanced Usages
• StreamReader Advanced Usages
• StreamReader Basic Usages
• StreamReader Basic Usages
• StreamReader Basic Usages
• StreamWriter
• StreamWriter
• StreamWriter Advanced Usage
• StreamWriter Advanced Usage
• StreamWriter Advanced Usage
• StreamWriter Basic Usage
• StreamWriter Basic Usage
• StreamWriter Basic Usage
• Streaming
• Streaming
• Streaming Video
• Streaming protocols
• StreamingMediaDecoder
• StreamingMediaDecoder
• StreamingMediaDecoder
• StreamingMediaDecoderCustomIO
• StreamingMediaEncoder
• StreamingMediaEncoder
• StreamingMediaEncoder
• StreamingMediaEncoderCustomIO
• Subtractive synthesis
• Subtractive synthesis
• Subtractive synthesis
• Summary
• Support Structure
• Support Structures
• Support Structures
• Support Structures
• Support Structures
• Support Structures
• Support Structures
• Supported Features
• Supported Features
• Sweeping cutoff frequency
• Synthetic source streams
• Synthetic source streams
• TACOTRON2_GRIFFINLIM_CHAR_LJSPEECH
• TACOTRON2_GRIFFINLIM_CHAR_LJSPEECH
• TACOTRON2_GRIFFINLIM_PHONE_LJSPEECH
• TACOTRON2_GRIFFINLIM_PHONE_LJSPEECH
• TACOTRON2_WAVERNN_CHAR_LJSPEECH
• TACOTRON2_WAVERNN_CHAR_LJSPEECH
• TACOTRON2_WAVERNN_PHONE_LJSPEECH
• TACOTRON2_WAVERNN_PHONE_LJSPEECH
• TEDLIUM
• TEDLIUM
• Tacotron2
• Tacotron2
• Tacotron2 Text-To-Speech
• Tacotron2 Text-To-Speech
• Tacotron2TTSBundle
• Tacotron2TTSBundle
• Tacotron2TTSBundle.TextProcessor
• Tacotron2TTSBundle.TextProcessor
• Tacotron2TTSBundle.Vocoder
• Tacotron2TTSBundle.Vocoder
• Text Processing
• Text-to-Speech with Tacotron2
• Text-to-Speech with Tacotron2
• Text-to-Speech with Tacotron2
• The basic usage
• The effect of n_fft parameter
• Time and Frequency Masking
• TimeMasking
• TimeMasking
• TimeStretch
• TimeStretch
• TimeStretch
• Timestep Alignments
• Tips on slicing
• Token-level alignments
• TokenSpan
• TokenSpan
• Tokenize the transcript
• Tokens
• Tokens
• TorchAudio Logo
• TorchAudio Logo
• TorchScript
• Torchaudio Documentation
• Torchaudio Documentation
• Torchaudio-Squim: Non-intrusive Speech Assessment in TorchAudio
• Torchaudio-Squim: Non-intrusive Speech Assessment in TorchAudio
• Torchaudio-Squim: Non-intrusive Speech Assessment in TorchAudio
• Triangle wave
• Tutorials
• UDP (User Datagram Protocol)
• Upsample (44.1 -> 48 kHz)
• Upsample (8 -> 16 kHz)
• Usage
• Using the GPU decoder/encoder from TorchAudio
• Using the hardware decoder and encoder
• Utilities
• Utility
• Utility
• Utility
• Utility Functions
• VCTK_092
• VCTK_092
• VGA
• VGA
• VGGISH
• VGGISH
• VGGish
• VGGishBundle
• VGGishBundle
• VGGishBundle.VGGish
• VGGishBundle.VGGish
• VGGishBundle.VGGishInputProcessor
• VGGishBundle.VGGishInputProcessor
• VOXPOPULI_ASR_BASE_10K_DE
• VOXPOPULI_ASR_BASE_10K_DE
• VOXPOPULI_ASR_BASE_10K_EN
• VOXPOPULI_ASR_BASE_10K_EN
• VOXPOPULI_ASR_BASE_10K_ES
• VOXPOPULI_ASR_BASE_10K_ES
• VOXPOPULI_ASR_BASE_10K_FR
• VOXPOPULI_ASR_BASE_10K_FR
• VOXPOPULI_ASR_BASE_10K_IT
• VOXPOPULI_ASR_BASE_10K_IT
• Vad
• Vad
• Vectors
• Vertical
• Video Examples
• Video Examples
• Video Stream
• Visualization
• Visualization
• Visualization
• Visualization
• Visualization
• Visualization
• Visualization
• Visualization
• Vol
• Vol
• Vorbis
• VoxCeleb1Identification
• VoxCeleb1Identification
• VoxCeleb1Verification
• VoxCeleb1Verification
• WAV2VEC2_ASR_BASE_100H
• WAV2VEC2_ASR_BASE_100H
• WAV2VEC2_ASR_BASE_10M
• WAV2VEC2_ASR_BASE_10M
• WAV2VEC2_ASR_BASE_960H
• WAV2VEC2_ASR_BASE_960H
• WAV2VEC2_ASR_LARGE_100H
• WAV2VEC2_ASR_LARGE_100H
• WAV2VEC2_ASR_LARGE_10M
• WAV2VEC2_ASR_LARGE_10M
• WAV2VEC2_ASR_LARGE_960H
• WAV2VEC2_ASR_LARGE_960H
• WAV2VEC2_ASR_LARGE_LV60K_100H
• WAV2VEC2_ASR_LARGE_LV60K_100H
• WAV2VEC2_ASR_LARGE_LV60K_10M
• WAV2VEC2_ASR_LARGE_LV60K_10M
• WAV2VEC2_ASR_LARGE_LV60K_960H
• WAV2VEC2_ASR_LARGE_LV60K_960H
• WAV2VEC2_BASE
• WAV2VEC2_BASE
• WAV2VEC2_LARGE
• WAV2VEC2_LARGE
• WAV2VEC2_LARGE_LV60K
• WAV2VEC2_LARGE_LV60K
• WAV2VEC2_XLSR53
• WAV2VEC2_XLSR53
• WAV2VEC2_XLSR_1B
• WAV2VEC2_XLSR_1B
• WAV2VEC2_XLSR_2B
• WAV2VEC2_XLSR_2B
• WAV2VEC2_XLSR_300M
• WAV2VEC2_XLSR_300M
• WAVLM_BASE
• WAVLM_BASE
• WAVLM_BASE_PLUS
• WAVLM_BASE_PLUS
• WAVLM_LARGE
• WAVLM_LARGE
• Wah-wah effects
• Wav2Letter
• Wav2Letter
• Wav2Vec2ASRBundle
• Wav2Vec2ASRBundle
• Wav2Vec2Bundle
• Wav2Vec2Bundle
• Wav2Vec2FABundle
• Wav2Vec2FABundle
• Wav2Vec2FABundle.Aligner
• Wav2Vec2FABundle.Aligner
• Wav2Vec2FABundle.Tokenizer
• Wav2Vec2FABundle.Tokenizer
• Wav2Vec2Model
• Wav2Vec2Model
• WaveRNN
• WaveRNN
• WaveRNN Vocoder
• Waveform Generation
• Waveglow Vocoder
• Window function
• Windowed-Sinc Filter
• Windowed-sinc filter
• Word-level alignments
• Write Video
• Write data
• Write destination
• Write methods
• Writing data chunk by chunk
• XGA
• XGA
• YESNO
• YESNO
• [Optional] Build TorchAudio with a custom FFmpeg
• [Optional] Build TorchAudio with a custom built FFmpeg
• [Optional] Building FFmpeg from source
• __call__
• __call__
• __call__
• __call__
• __call__
• __call__
• __call__
• __call__
• __call__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• __getitem__
• add_audio_stream
• add_audio_stream
• add_audio_stream
• add_audio_stream
• add_basic_audio_stream
• add_basic_video_stream
• add_video_stream
• add_video_stream
• add_video_stream
• add_video_stream
• additional parameters
• allpass
• apply
• bandpass
• bandreject
• beam size
• beam size
• beam size token
• beam threshold
• bit_rate=192k
• bit_rate=8k
• blank skip threshold
• chorus
• classtorio_1_1io_1_1StreamingMediaDecoder
• classtorio_1_1io_1_1StreamingMediaDecoderCustomIO
• classtorio_1_1io_1_1StreamingMediaDecoderCustomIO_1a202cf89aab3628148e72a804f13e90f4
• classtorio_1_1io_1_1StreamingMediaDecoder_1a01014e8d07967bcd99cf79409bc4026b
• classtorio_1_1io_1_1StreamingMediaDecoder_1a01fdf9e71bd58aeafcf2aeb4418a817c
• classtorio_1_1io_1_1StreamingMediaDecoder_1a0f4f370219d1615b3b5222aa5385f42b
• classtorio_1_1io_1_1StreamingMediaDecoder_1a2675b80361ce5ac9da29bb63105f1135
• classtorio_1_1io_1_1StreamingMediaDecoder_1a2949d852664329f6cdc84122ae04c3c3
• classtorio_1_1io_1_1StreamingMediaDecoder_1a47015d7637b5c24376ba1c9cac442cdb
• classtorio_1_1io_1_1StreamingMediaDecoder_1a4dbd058266fd2876508d87ec98adb978
• classtorio_1_1io_1_1StreamingMediaDecoder_1a6901f6138d5bc2c7dc0e2919960aa378
• classtorio_1_1io_1_1StreamingMediaDecoder_1a69a405cbf490b82bc23e7d8dae9991a7
• classtorio_1_1io_1_1StreamingMediaDecoder_1a6b3e5fd480cc50ee5ec9b389641c4512
• classtorio_1_1io_1_1StreamingMediaDecoder_1ab435622f836a58a577a27f0bea8f5819
• classtorio_1_1io_1_1StreamingMediaDecoder_1ab79ca75fbcf46543b5947762d4feba46
• classtorio_1_1io_1_1StreamingMediaDecoder_1ac00e054c55f2187d7dd6ed9ba21d2228
• classtorio_1_1io_1_1StreamingMediaDecoder_1ae3f5ab23b21ee6d2e5a2ed8c53dc260d
• classtorio_1_1io_1_1StreamingMediaDecoder_1ae41fbb0c7e92538ba68557a815e09b15
• classtorio_1_1io_1_1StreamingMediaDecoder_1af0c02f604589f887e6d4581a7f4a3b17
• classtorio_1_1io_1_1StreamingMediaDecoder_1af443fa8e8ac186ac4404d81ea3bec59c
• classtorio_1_1io_1_1StreamingMediaEncoder
• classtorio_1_1io_1_1StreamingMediaEncoderCustomIO
• classtorio_1_1io_1_1StreamingMediaEncoderCustomIO_1adbb9bd5b9630d44dfbc20a1f4f24dcd7
• classtorio_1_1io_1_1StreamingMediaEncoder_1a0e21811fac24de6266ad31ef36c7175a
• classtorio_1_1io_1_1StreamingMediaEncoder_1a6f34d0b9887f3af40c4d4ec421ffe1d3
• classtorio_1_1io_1_1StreamingMediaEncoder_1a7785f86ab22716b0d6fcab72b43e0eea
• classtorio_1_1io_1_1StreamingMediaEncoder_1a7c1f0d545d84b6dcfe27655abfb23484
• classtorio_1_1io_1_1StreamingMediaEncoder_1a9a0a1eb7632782ca3505f4c006e63351
• classtorio_1_1io_1_1StreamingMediaEncoder_1aac942a7abc08bc215fd0a62233f623da
• classtorio_1_1io_1_1StreamingMediaEncoder_1ab8dbb3b62454618d83a25fb255de91df
• classtorio_1_1io_1_1StreamingMediaEncoder_1ac192ea68a58042c6ffe5001f3ef8b49b
• classtorio_1_1io_1_1StreamingMediaEncoder_1ad4b54cba53a7564bb058ede079ff6530
• clear_cuda_context_cache
• clear_cuda_context_cache
• close
• close
• compression_level=1
• compression_level=9
• crystalizer
• ctc_decoder
• ctc_decoder
• cuda_ctc_decoder
• cuda_ctc_decoder
• decode_begin
• decode_end
• decode_step
• default
• default_audio_stream
• default_video_stream
• download_pretrained_files
• download_pretrained_files
• echo
• extract_features
• ffmpeg_dependency
• ffmpeg_utils
• ffmpeg_utils
• ffmpeg_utils
• ffmpeg_utils
• fft filter
• fill_buffer
• fill_buffer
• find_best_audio_stream
• find_best_video_stream
• flanger
• flush
• flush
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• forward
• get_aligner
• get_audio_decoders
• get_audio_decoders
• get_audio_encoders
• get_audio_encoders
• get_buffer_size
• get_build_config
• get_build_config
• get_decoder
• get_demuxers
• get_demuxers
• get_dict
• get_feature_extractor
• get_final_hypothesis
• get_input_devices
• get_input_devices
• get_input_processor
• get_input_protocols
• get_input_protocols
• get_labels
• get_labels
• get_log_level
• get_log_level
• get_mel_transform
• get_metadata
• get_metadata
• get_metadata
• get_metadata
• get_metadata
• get_metadata
• get_metadata
• get_metadata
• get_metadata
• get_metadata
• get_metadata
• get_metadata
• get_model
• get_model
• get_model
• get_model
• get_model
• get_model
• get_model
• get_muxers
• get_muxers
• get_out_stream_info
• get_out_stream_info
• get_output_devices
• get_output_devices
• get_output_protocols
• get_output_protocols
• get_src_stream_info
• get_src_stream_info
• get_streaming_feature_extractor
• get_tacotron2
• get_text_processor
• get_token_processor
• get_tokenizer
• get_versions
• get_versions
• get_video_decoders
• get_video_decoders
• get_video_encoders
• get_video_encoders
• get_vocoder
• get_vocoder
• haas
• highpass
• hop_length
• idxs_to_tokens
• infer
• infer
• infer
• infer
• infer
• is_buffer_ready
• is_buffer_ready
• join
• kaiser_best
• kaiser_fast
• language model weight
• libtorio
• libtorio
• list_effects
• list_read_formats
• list_write_formats
• lowpass
• mp3
• n_fft
• n_mels
• nbest
• nbest
• num_out_streams
• num_out_streams
• num_src_streams
• num_src_streams
• nvdec_tutorial
• nvenc_tutorial
• ogg
• ogg - default encoder (flac)
• ogg - opus
• ogg - vorbis
• open
• open
• phaser
• phoneme_dict
• play_audio
• play_audio
• pop_chunks
• pop_chunks
• predict
• process_all_packets
• process_all_packets
• process_packet
• process_packet
• process_packet_block
• pulsator
• qscale=1
• qscale=9
• read_mat_ark
• read_mat_scp
• read_vec_flt_ark
• read_vec_flt_scp
• read_vec_int_ark
• remove_stream
• remove_stream
• right_context_length
• sample_rate
• sample_rate
• sample_rate
• sample_rate
• sample_rate
• sample_rate
• sample_rate
• sample_rate
• sample_rate
• sample_rate
• seek
• seek
• segment_length
• set_buffer_size
• set_log_level
• set_log_level
• set_metadata
• set_metadata
• set_seed
• set_use_threads
• set_verbosity
• sox_utils
• sox_utils
• sphx_glr_download_tutorials_additive_synthesis_tutorial.py
• sphx_glr_download_tutorials_asr_inference_with_ctc_decoder_tutorial.py
• sphx_glr_download_tutorials_asr_inference_with_cuda_ctc_decoder_tutorial.py
• sphx_glr_download_tutorials_audio_data_augmentation_tutorial.py
• sphx_glr_download_tutorials_audio_datasets_tutorial.py
• sphx_glr_download_tutorials_audio_feature_augmentation_tutorial.py
• sphx_glr_download_tutorials_audio_feature_extractions_tutorial.py
• sphx_glr_download_tutorials_audio_io_tutorial.py
• sphx_glr_download_tutorials_audio_resampling_tutorial.py
• sphx_glr_download_tutorials_ctc_forced_alignment_api_tutorial.py
• sphx_glr_download_tutorials_device_asr.py
• sphx_glr_download_tutorials_device_avsr.py
• sphx_glr_download_tutorials_effector_tutorial.py
• sphx_glr_download_tutorials_filter_design_tutorial.py
• sphx_glr_download_tutorials_forced_alignment_for_multilingual_data_tutorial.py
• sphx_glr_download_tutorials_forced_alignment_tutorial.py
• sphx_glr_download_tutorials_hybrid_demucs_tutorial.py
• sphx_glr_download_tutorials_mvdr_tutorial.py
• sphx_glr_download_tutorials_nvdec_tutorial.py
• sphx_glr_download_tutorials_nvenc_tutorial.py
• sphx_glr_download_tutorials_online_asr_tutorial.py
• sphx_glr_download_tutorials_oscillator_tutorial.py
• sphx_glr_download_tutorials_speech_recognition_pipeline_tutorial.py
• sphx_glr_download_tutorials_squim_tutorial.py
• sphx_glr_download_tutorials_streamreader_advanced_tutorial.py
• sphx_glr_download_tutorials_streamreader_basic_tutorial.py
• sphx_glr_download_tutorials_streamwriter_advanced.py
• sphx_glr_download_tutorials_streamwriter_basic_tutorial.py
• sphx_glr_download_tutorials_subtractive_synthesis_tutorial.py
• sphx_glr_download_tutorials_tacotron2_pipeline_tutorial.py
• stream
• stream
• structtorio_1_1io_1_1Chunk
• structtorio_1_1io_1_1Chunk_1a6b4f6a8b707901b3b10ef2d7df2e3e4d
• structtorio_1_1io_1_1Chunk_1a9d15ed58a3e748508e5ac9b2f39f5be5
• structtorio_1_1io_1_1OutputStreamInfo
• structtorio_1_1io_1_1OutputStreamInfo_1a27a775f9402919c3e48a3bc63cd19414
• structtorio_1_1io_1_1OutputStreamInfo_1a28f3b8e320a2d620b132acf3cff24715
• structtorio_1_1io_1_1OutputStreamInfo_1a41688027e3c680fc3e43f2bc5834d745
• structtorio_1_1io_1_1OutputStreamInfo_1a5fbe6e8d7efede48e86d5fa52c82f0b0
• structtorio_1_1io_1_1OutputStreamInfo_1a77441472f664aae0434bc2c332f6790e
• structtorio_1_1io_1_1OutputStreamInfo_1a7fa46a5796af9b560c93dd3688052b7a
• structtorio_1_1io_1_1OutputStreamInfo_1abf0481abb45d23afe25806f149fdee44
• structtorio_1_1io_1_1OutputStreamInfo_1af0796c137d1d62d61fb505b7ddc60a50
• structtorio_1_1io_1_1OutputStreamInfo_1afb5bc0d1918e188b27d8273bd04511c7
• structtorio_1_1io_1_1SrcStreamInfo
• structtorio_1_1io_1_1SrcStreamInfo_1a0c1c2812bbd202ca42913d6b6b81b597
• structtorio_1_1io_1_1SrcStreamInfo_1a15fb5310df582da99644c0cfe9cda926
• structtorio_1_1io_1_1SrcStreamInfo_1a1610ecb097b5769f2355b663956bda75
• structtorio_1_1io_1_1SrcStreamInfo_1a7445147c98842da1e0a17a532a5a1882
• structtorio_1_1io_1_1SrcStreamInfo_1a92f5b3eee0a9191ac9b941813e59a39f
• structtorio_1_1io_1_1SrcStreamInfo_1ab395c00d4a21aada8eaf9a26219010e6
• structtorio_1_1io_1_1SrcStreamInfo_1abacd6778fbed84e9813e2d0d12b2f6e9
• structtorio_1_1io_1_1SrcStreamInfo_1abb1dbb8e70a976dd6b8e6960f4f36313
• structtorio_1_1io_1_1SrcStreamInfo_1acff9793602878574a5b4bcb3e69b9b28
• structtorio_1_1io_1_1SrcStreamInfo_1aedaf37cd17c18485f2f2dcc81d8fa1ca
• structtorio_1_1io_1_1SrcStreamInfo_1af513beba4aa8a4d938340b1155436e2d
• structtorio_1_1io_1_1SrcStreamInfo_1af63a840ef28286d0c8a72dfa79d2093b
• structtorio_1_1io_1_1SrcStreamInfo_1afbb856b739941b2c7baf41f68d888767
• symbols
• tempo
• tokens
• torchaudio
• torchaudio
• torchaudio.compliance.kaldi
• torchaudio.compliance.kaldi
• torchaudio.compliance.kaldi.fbank
• torchaudio.compliance.kaldi.fbank
• torchaudio.compliance.kaldi.mfcc
• torchaudio.compliance.kaldi.mfcc
• torchaudio.compliance.kaldi.spectrogram
• torchaudio.compliance.kaldi.spectrogram
• torchaudio.datasets
• torchaudio.datasets
• torchaudio.functional
• torchaudio.functional
• torchaudio.functional.DB_to_amplitude
• torchaudio.functional.DB_to_amplitude
• torchaudio.functional.add_noise
• torchaudio.functional.add_noise
• torchaudio.functional.allpass_biquad
• torchaudio.functional.allpass_biquad
• torchaudio.functional.amplitude_to_DB
• torchaudio.functional.amplitude_to_DB
• torchaudio.functional.apply_beamforming
• torchaudio.functional.apply_beamforming
• torchaudio.functional.apply_codec
• torchaudio.functional.apply_codec
• torchaudio.functional.band_biquad
• torchaudio.functional.band_biquad
• torchaudio.functional.bandpass_biquad
• torchaudio.functional.bandpass_biquad
• torchaudio.functional.bandreject_biquad
• torchaudio.functional.bandreject_biquad
• torchaudio.functional.bass_biquad
• torchaudio.functional.bass_biquad
• torchaudio.functional.biquad
• torchaudio.functional.biquad
• torchaudio.functional.compute_deltas
• torchaudio.functional.compute_deltas
• torchaudio.functional.contrast
• torchaudio.functional.contrast
• torchaudio.functional.convolve
• torchaudio.functional.convolve
• torchaudio.functional.create_dct
• torchaudio.functional.create_dct
• torchaudio.functional.dcshift
• torchaudio.functional.dcshift
• torchaudio.functional.deemph_biquad
• torchaudio.functional.deemph_biquad
• torchaudio.functional.deemphasis
• torchaudio.functional.deemphasis
• torchaudio.functional.detect_pitch_frequency
• torchaudio.functional.detect_pitch_frequency
• torchaudio.functional.dither
• torchaudio.functional.dither
• torchaudio.functional.edit_distance
• torchaudio.functional.edit_distance
• torchaudio.functional.equalizer_biquad
• torchaudio.functional.equalizer_biquad
• torchaudio.functional.fftconvolve
• torchaudio.functional.fftconvolve
• torchaudio.functional.filtfilt
• torchaudio.functional.filtfilt
• torchaudio.functional.flanger
• torchaudio.functional.flanger
• torchaudio.functional.forced_align
• torchaudio.functional.forced_align
• torchaudio.functional.frechet_distance
• torchaudio.functional.frechet_distance
• torchaudio.functional.gain
• torchaudio.functional.gain
• torchaudio.functional.griffinlim
• torchaudio.functional.griffinlim
• torchaudio.functional.highpass_biquad
• torchaudio.functional.highpass_biquad
• torchaudio.functional.inverse_spectrogram
• torchaudio.functional.inverse_spectrogram
• torchaudio.functional.lfilter
• torchaudio.functional.lfilter
• torchaudio.functional.linear_fbanks
• torchaudio.functional.linear_fbanks
• torchaudio.functional.loudness
• torchaudio.functional.loudness
• torchaudio.functional.lowpass_biquad
• torchaudio.functional.lowpass_biquad
• torchaudio.functional.mask_along_axis
• torchaudio.functional.mask_along_axis
• torchaudio.functional.mask_along_axis_iid
• torchaudio.functional.mask_along_axis_iid
• torchaudio.functional.melscale_fbanks
• torchaudio.functional.melscale_fbanks
• torchaudio.functional.merge_tokens
• torchaudio.functional.merge_tokens
• torchaudio.functional.mu_law_decoding
• torchaudio.functional.mu_law_decoding
• torchaudio.functional.mu_law_encoding
• torchaudio.functional.mu_law_encoding
• torchaudio.functional.mvdr_weights_rtf
• torchaudio.functional.mvdr_weights_rtf
• torchaudio.functional.mvdr_weights_souden
• torchaudio.functional.mvdr_weights_souden
• torchaudio.functional.overdrive
• torchaudio.functional.overdrive
• torchaudio.functional.phase_vocoder
• torchaudio.functional.phase_vocoder
• torchaudio.functional.phaser
• torchaudio.functional.phaser
• torchaudio.functional.pitch_shift
• torchaudio.functional.pitch_shift
• torchaudio.functional.preemphasis
• torchaudio.functional.preemphasis
• torchaudio.functional.psd
• torchaudio.functional.psd
• torchaudio.functional.resample
• torchaudio.functional.resample
• torchaudio.functional.riaa_biquad
• torchaudio.functional.riaa_biquad
• torchaudio.functional.rnnt_loss
• torchaudio.functional.rnnt_loss
• torchaudio.functional.rtf_evd
• torchaudio.functional.rtf_evd
• torchaudio.functional.rtf_power
• torchaudio.functional.rtf_power
• torchaudio.functional.sliding_window_cmn
• torchaudio.functional.sliding_window_cmn
• torchaudio.functional.spectral_centroid
• torchaudio.functional.spectral_centroid
• torchaudio.functional.spectrogram
• torchaudio.functional.spectrogram
• torchaudio.functional.speed
• torchaudio.functional.speed
• torchaudio.functional.treble_biquad
• torchaudio.functional.treble_biquad
• torchaudio.functional.vad
• torchaudio.functional.vad
• torchaudio.info
• torchaudio.info
• torchaudio.io
• torchaudio.io
• torchaudio.kaldi_io
• torchaudio.list_audio_backends
• torchaudio.list_audio_backends
• torchaudio.load
• torchaudio.load
• torchaudio.models
• torchaudio.models
• torchaudio.models.conv_tasnet_base
• torchaudio.models.conv_tasnet_base
• torchaudio.models.decoder
• torchaudio.models.decoder
• torchaudio.models.emformer_rnnt_base
• torchaudio.models.emformer_rnnt_base
• torchaudio.models.emformer_rnnt_model
• torchaudio.models.emformer_rnnt_model
• torchaudio.models.hdemucs_high
• torchaudio.models.hdemucs_high
• torchaudio.models.hdemucs_low
• torchaudio.models.hdemucs_low
• torchaudio.models.hdemucs_medium
• torchaudio.models.hdemucs_medium
• torchaudio.models.hubert_base
• torchaudio.models.hubert_base
• torchaudio.models.hubert_large
• torchaudio.models.hubert_large
• torchaudio.models.hubert_pretrain_base
• torchaudio.models.hubert_pretrain_base
• torchaudio.models.hubert_pretrain_large
• torchaudio.models.hubert_pretrain_large
• torchaudio.models.hubert_pretrain_model
• torchaudio.models.hubert_pretrain_model
• torchaudio.models.hubert_pretrain_xlarge
• torchaudio.models.hubert_pretrain_xlarge
• torchaudio.models.hubert_xlarge
• torchaudio.models.hubert_xlarge
• torchaudio.models.squim_objective_base
• torchaudio.models.squim_objective_base
• torchaudio.models.squim_objective_model
• torchaudio.models.squim_objective_model
• torchaudio.models.squim_subjective_base
• torchaudio.models.squim_subjective_base
• torchaudio.models.squim_subjective_model
• torchaudio.models.squim_subjective_model
• torchaudio.models.wav2vec2.utils.import_fairseq_model
• torchaudio.models.wav2vec2.utils.import_fairseq_model
• torchaudio.models.wav2vec2.utils.import_huggingface_model
• torchaudio.models.wav2vec2.utils.import_huggingface_model
• torchaudio.models.wav2vec2_base
• torchaudio.models.wav2vec2_base
• torchaudio.models.wav2vec2_large
• torchaudio.models.wav2vec2_large
• torchaudio.models.wav2vec2_large_lv60k
• torchaudio.models.wav2vec2_large_lv60k
• torchaudio.models.wav2vec2_model
• torchaudio.models.wav2vec2_model
• torchaudio.models.wav2vec2_xlsr_1b
• torchaudio.models.wav2vec2_xlsr_1b
• torchaudio.models.wav2vec2_xlsr_2b
• torchaudio.models.wav2vec2_xlsr_2b
• torchaudio.models.wav2vec2_xlsr_300m
• torchaudio.models.wav2vec2_xlsr_300m
• torchaudio.models.wavlm_base
• torchaudio.models.wavlm_base
• torchaudio.models.wavlm_large
• torchaudio.models.wavlm_large
• torchaudio.models.wavlm_model
• torchaudio.models.wavlm_model
• torchaudio.pipelines
• torchaudio.pipelines
• torchaudio.prototype
• torchaudio.prototype
• torchaudio.prototype.datasets
• torchaudio.prototype.datasets
• torchaudio.prototype.functional
• torchaudio.prototype.functional.adsr_envelope
• torchaudio.prototype.functional.adsr_envelope
• torchaudio.prototype.functional.barkscale_fbanks
• torchaudio.prototype.functional.barkscale_fbanks
• torchaudio.prototype.functional.chroma_filterbank
• torchaudio.prototype.functional.chroma_filterbank
• torchaudio.prototype.functional.extend_pitch
• torchaudio.prototype.functional.extend_pitch
• torchaudio.prototype.functional.filter_waveform
• torchaudio.prototype.functional.filter_waveform
• torchaudio.prototype.functional.frequency_impulse_response
• torchaudio.prototype.functional.frequency_impulse_response
• torchaudio.prototype.functional.oscillator_bank
• torchaudio.prototype.functional.oscillator_bank
• torchaudio.prototype.functional.ray_tracing
• torchaudio.prototype.functional.ray_tracing
• torchaudio.prototype.functional.simulate_rir_ism
• torchaudio.prototype.functional.simulate_rir_ism
• torchaudio.prototype.functional.sinc_impulse_response
• torchaudio.prototype.functional.sinc_impulse_response
• torchaudio.prototype.models
• torchaudio.prototype.models.conformer_rnnt_base
• torchaudio.prototype.models.conformer_rnnt_base
• torchaudio.prototype.models.conformer_rnnt_model
• torchaudio.prototype.models.conformer_rnnt_model
• torchaudio.prototype.models.conformer_wav2vec2_base
• torchaudio.prototype.models.conformer_wav2vec2_base
• torchaudio.prototype.models.conformer_wav2vec2_model
• torchaudio.prototype.models.conformer_wav2vec2_model
• torchaudio.prototype.models.conformer_wav2vec2_pretrain_base
• torchaudio.prototype.models.conformer_wav2vec2_pretrain_base
• torchaudio.prototype.models.conformer_wav2vec2_pretrain_large
• torchaudio.prototype.models.conformer_wav2vec2_pretrain_large
• torchaudio.prototype.models.conformer_wav2vec2_pretrain_model
• torchaudio.prototype.models.conformer_wav2vec2_pretrain_model
• torchaudio.prototype.models.emformer_hubert_base
• torchaudio.prototype.models.emformer_hubert_base
• torchaudio.prototype.models.emformer_hubert_model
• torchaudio.prototype.models.emformer_hubert_model
• torchaudio.prototype.models.hifigan_vocoder
• torchaudio.prototype.models.hifigan_vocoder
• torchaudio.prototype.models.hifigan_vocoder_v1
• torchaudio.prototype.models.hifigan_vocoder_v1
• torchaudio.prototype.models.hifigan_vocoder_v2
• torchaudio.prototype.models.hifigan_vocoder_v2
• torchaudio.prototype.models.hifigan_vocoder_v3
• torchaudio.prototype.models.hifigan_vocoder_v3
• torchaudio.prototype.pipelines
• torchaudio.prototype.transforms
• torchaudio.prototype.transforms
• torchaudio.save
• torchaudio.save
• torchaudio.sox_effects
• torchaudio.sox_effects
• torchaudio.sox_effects.apply_effects_file
• torchaudio.sox_effects.apply_effects_file
• torchaudio.sox_effects.apply_effects_tensor
• torchaudio.sox_effects.apply_effects_tensor
• torchaudio.sox_effects.effect_names
• torchaudio.sox_effects.effect_names
• torchaudio.transforms
• torchaudio.transforms
• torchaudio.utils
• torchaudio.utils
• torio
• torio
• torio.io
• torio.io
• torio.utils
• torio.utils
• torio::io::StreamingMediaDecoder
• torio::io::StreamingMediaDecoder
• torio::io::StreamingMediaEncoder
• torio::io::StreamingMediaEncoder
• transcribe
• transcribe_streaming
• tremolo
• vibrato
• wav2vec 2.0 / HuBERT - Fine-tuned ASR
• wav2vec 2.0 / HuBERT - Forced Alignment
• wav2vec 2.0 / HuBERT / WavLM - SSL
• write_audio_chunk
• write_audio_chunk
• write_video_chunk
• write_video_chunk

Values

• torchaudio.models.Hypothesis
• torchaudio.pipelines.CONVTASNET_BASE_LIBRI2MIX
• torchaudio.pipelines.EMFORMER_RNNT_BASE_LIBRISPEECH
• torchaudio.pipelines.HDEMUCS_HIGH_MUSDB
• torchaudio.pipelines.HDEMUCS_HIGH_MUSDB_PLUS
• torchaudio.pipelines.HUBERT_ASR_LARGE
• torchaudio.pipelines.HUBERT_ASR_XLARGE
• torchaudio.pipelines.HUBERT_BASE
• torchaudio.pipelines.HUBERT_LARGE
• torchaudio.pipelines.HUBERT_XLARGE
• torchaudio.pipelines.MMS_FA
• torchaudio.pipelines.SQUIM_OBJECTIVE
• torchaudio.pipelines.SQUIM_SUBJECTIVE
• torchaudio.pipelines.TACOTRON2_GRIFFINLIM_CHAR_LJSPEECH
• torchaudio.pipelines.TACOTRON2_GRIFFINLIM_PHONE_LJSPEECH
• torchaudio.pipelines.TACOTRON2_WAVERNN_CHAR_LJSPEECH
• torchaudio.pipelines.TACOTRON2_WAVERNN_PHONE_LJSPEECH
• torchaudio.pipelines.VOXPOPULI_ASR_BASE_10K_DE
• torchaudio.pipelines.VOXPOPULI_ASR_BASE_10K_EN
• torchaudio.pipelines.VOXPOPULI_ASR_BASE_10K_ES
• torchaudio.pipelines.VOXPOPULI_ASR_BASE_10K_FR
• torchaudio.pipelines.VOXPOPULI_ASR_BASE_10K_IT
• torchaudio.pipelines.WAV2VEC2_ASR_BASE_100H
• torchaudio.pipelines.WAV2VEC2_ASR_BASE_10M
• torchaudio.pipelines.WAV2VEC2_ASR_BASE_960H
• torchaudio.pipelines.WAV2VEC2_ASR_LARGE_100H
• torchaudio.pipelines.WAV2VEC2_ASR_LARGE_10M
• torchaudio.pipelines.WAV2VEC2_ASR_LARGE_960H
• torchaudio.pipelines.WAV2VEC2_ASR_LARGE_LV60K_100H
• torchaudio.pipelines.WAV2VEC2_ASR_LARGE_LV60K_10M
• torchaudio.pipelines.WAV2VEC2_ASR_LARGE_LV60K_960H
• torchaudio.pipelines.WAV2VEC2_BASE
• torchaudio.pipelines.WAV2VEC2_LARGE
• torchaudio.pipelines.WAV2VEC2_LARGE_LV60K
• torchaudio.pipelines.WAV2VEC2_XLSR53
• torchaudio.pipelines.WAV2VEC2_XLSR_1B
• torchaudio.pipelines.WAV2VEC2_XLSR_2B
• torchaudio.pipelines.WAV2VEC2_XLSR_300M
• torchaudio.pipelines.WAVLM_BASE
• torchaudio.pipelines.WAVLM_BASE_PLUS
• torchaudio.pipelines.WAVLM_LARGE
• torchaudio.prototype.pipelines.EMFORMER_RNNT_BASE_MUSTC
• torchaudio.prototype.pipelines.EMFORMER_RNNT_BASE_TEDLIUM3
• torchaudio.prototype.pipelines.HIFIGAN_VOCODER_V3_LJSPEECH
• torchaudio.prototype.pipelines.VGGISH