Function reference • torchaudio

Datasets
`cmuarctic_dataset()`	CMU Arctic Dataset
`speechcommand_dataset()`	Speech Commands Dataset
`yesno_dataset()`	YesNo Dataset
Transforms
`transform__axismasking()`	Axis Masking
`transform_amplitude_to_db()`	Amplitude to DB
`transform_complex_norm()`	Complex Norm
`transform_compute_deltas()`	Delta Coefficients
`transform_fade()`	Fade In/Out
`transform_frequencymasking()`	Frequency-domain Masking
`transform_inverse_mel_scale()`	Inverse Mel Scale
`transform_mel_scale()`	Mel Scale
`transform_mel_spectrogram()`	Mel Spectrogram
`transform_mfcc()`	Mel-frequency Cepstrum Coefficients
`transform_mu_law_decoding()`	Mu Law Decoding
`transform_mu_law_encoding()`	Mu Law Encoding
`transform_resample()`	Signal Resample
`transform_sliding_window_cmn()`	sliding-window Cepstral Mean Normalization
`transform_spectrogram()`	Spectrogram
`transform_time_stretch()`	Time Stretch
`transform_timemasking()`	Time-domain Masking
`transform_to_tensor()`	Convert an audio object into a tensor
`transform_vad()`	Voice Activity Detector
`transform_vol()`	Add a volume to an waveform.
Functionals
`functional__combine_max()`	Combine Max (functional)
`functional__compute_nccf()`	Normalized Cross-Correlation Function (functional)
`functional__find_max_per_frame()`	Find Max Per Frame (functional)
`functional__generate_wave_table()`	Wave Table Generator (functional)
`functional__median_smoothing()`	Median Smoothing (functional)
`functional_add_noise_shaping()`	Noise Shaping (functional)
`functional_allpass_biquad()`	All-pass Biquad Filter (functional)
`functional_amplitude_to_db()`	Amplitude to DB (functional)
`functional_angle()`	Angle (functional)
`functional_apply_probability_distribution()`	Probability Distribution Apply (functional)
`functional_band_biquad()`	Two-pole Band Filter (functional)
`functional_bandpass_biquad()`	Band-pass Biquad Filter (functional)
`functional_bandreject_biquad()`	Band-reject Biquad Filter (functional)
`functional_bass_biquad()`	Bass Tone-control Effect (functional)
`functional_biquad()`	Biquad Filter (functional)
`functional_complex_norm()`	Complex Norm (functional)
`functional_compute_deltas()`	Delta Coefficients (functional)
`functional_contrast()`	Contrast Effect (functional)
`functional_create_dct()`	DCT transformation matrix (functional)
`functional_create_fb_matrix()`	Frequency Bin Conversion Matrix (functional)
`functional_db_to_amplitude()`	DB to Amplitude (functional)
`functional_dcshift()`	DC Shift (functional)
`functional_deemph_biquad()`	ISO 908 CD De-emphasis IIR Filter (functional)
`functional_detect_pitch_frequency()`	Detect Pitch Frequency (functional)
`functional_dither()`	Dither (functional)
`functional_equalizer_biquad()`	Biquad Peaking Equalizer Filter (functional)
`functional_flanger()`	Flanger Effect (functional)
`functional_gain()`	Gain (functional)
`functional_griffinlim()`	Griffin-Lim Transformation (functional)
`functional_highpass_biquad()`	High-pass Biquad Filter (functional)
`functional_lfilter()`	An IIR Filter (functional)
`functional_lowpass_biquad()`	Low-pass Biquad Filter (functional)
`functional_magphase()`	Magnitude and Phase (functional)
`functional_mask_along_axis()`	Mask Along Axis (functional)
`functional_mask_along_axis_iid()`	Mask Along Axis IID (functional)
`functional_mel_scale()`	Mel Scale (functional)
`functional_mu_law_decoding()`	Mu Law Decoding (functional)
`functional_mu_law_encoding()`	Mu Law Encoding (functional)
`functional_overdrive()`	Overdrive Effect (functional)
`functional_phase_vocoder()`	Phase Vocoder
`functional_phaser()`	Phasing Effect (functional)
`functional_riaa_biquad()`	RIAA Vinyl Playback Equalisation (functional)
`functional_sliding_window_cmn()`	sliding-window Cepstral Mean Normalization (functional)
`functional_spectrogram()`	Spectrogram (functional)
`functional_treble_biquad()`	Treble Tone-control Effect (functional)
`functional_vad()`	Voice Activity Detector (functional)
Kaldi API
`kaldi__get_lr_indices_and_weights()`	Linear Resample Indices And Weights
`kaldi__get_num_lr_output_samples()`	Linear Resample Output Samples
`kaldi_resample_waveform()`	Kaldi's Resample Waveform
`list_audio_backends()`	List available audio backends
Neural network modules
`model_melresnet()`	MelResNet
`model_resblock()`	ResBlock
`model_stretch2d()`	Stretch2d
`model_upsample_network()`	UpsampleNetwork
`model_wavernn()`	WaveRNN
Audio I/O
`torchaudio_load()`	Load Audio File
Informational
`torchaudio_info()`	Audio Information
Utilities
`extract_archive()`	Extract Archive
Misc
`linear_to_mel_frequency()`	Linear to mel frequency
`mel_to_linear_frequency()`	Mel to linear frequency

Reference

Datasets

Transforms

Functionals

Kaldi API

Neural network modules

Audio I/O

Informational

Utilities

Misc