audtorch

Deep learning with PyTorch and audio.

Documentation: https://audtorch.readthedocs.io

If you are interested in PyTorch and audio you should also check out the efforts to integrate more audio directly into PyTorch:

• pytorch/audio
• keunwoochoi/torchaudio-contrib

Getting started

• Installation
• Usage
• Contributing
  • Development Installation
  • Pull requests
  • Writing Documentation
  • Building Documentation
  • Running Tests
  • Creating a New Release
• Version History

API Documentation

• audtorch.collate
  • Collation
  • Seq2Seq
• audtorch.datasets
  • AudioSet
  • LibriSpeech
  • MozillaCommonVoice
  • VoxCeleb1
  • WhiteNoise
  • Base
    • AudioDataset
    • PandasDataset
    • CsvDataset
    • AudioConcatDataset
  • Mixture
    • SpeechNoiseMix
  • Utils
    • load
    • download_url
    • download_url_list
    • extract_archive
    • sampling_rate_after_transform
    • ensure_same_sampling_rate
    • ensure_df_columns_contain
    • ensure_df_not_empty
    • files_and_labels_from_df
    • defined_split
• audtorch.metrics
  • EnergyConservingLoss
  • PearsonR
  • ConcordanceCC
• audtorch.metrics.functional
  • pearsonr
  • concordance_cc
• audtorch.samplers
  • BucketSampler
  • buckets_by_boundaries
  • buckets_of_even_size
• audtorch.transforms
  • Compose
  • Crop
  • RandomCrop
  • Pad
  • RandomPad
  • Replicate
  • RandomReplicate
  • Expand
  • Downmix
  • Upmix
  • Remix
  • Normalize
  • Resample
  • Spectrogram
  • LogSpectrogram
  • RandomAdditiveMix
• audtorch.transforms.functional
  • crop
  • pad
  • replicate
  • downmix
  • upmix
  • additive_mix
  • normalize
  • stft
  • istft
• audtorch.utils
  • flatten_list
  • to_tuple
  • energy
  • power
  • run_worker_threads
• References
• Index