aac_datasets.utils.typing module¶
- class AudioMetaData[source]¶
Bases:
objectReturn type of
torchaudio.infofunction.- Variables:
sample_rate (int) – Sample rate
num_frames (int) – The number of frames
num_channels (int) – The number of channels
bits_per_sample (int) – The number of bits per sample. This is 0 for lossy formats, or when it cannot be accurately inferred.
encoding (str) –
Audio encoding The values encoding can take are one of the following:
PCM_S: Signed integer linear PCMPCM_U: Unsigned integer linear PCMPCM_F: Floating point linear PCMFLAC: Flac, Free Lossless Audio CodecULAW: Mu-lawALAW: A-lawMP3: MP3, MPEG-1 Audio Layer IIIVORBIS: OGG VorbisAMR_WB: Adaptive Multi-Rate WidebandAMR_NB: Adaptive Multi-Rate NarrowbandOPUS: OpusHTK: Single channel 16-bit PCMUNKNOWN: None of above