auditok, an AUDIo TOKenization tool

auditok is an Audio Activity Detection tool that can process online data (read from an audio device or from standard input) as well as audio files. It can be used as a command line program or by calling its API.

Getting started

• Installation
• Load audio data
  • From a file
  • From a bytes object
  • From the microphone
  • Skip part of audio data
  • Limit the amount of read audio
• Basic split example
• Split and plot
• Read and split data from the microphone
• Access recorded data after split
• Working with AudioRegions
  • Basic region information
  • Concatenate regions
  • Repeat a region
  • Split one region into N regions of equal size
  • Slice a region by samples, seconds or milliseconds
  • Get arrays of audio samples

Command-line guide

• Read and split audio data online
• Read audio data with an external program
• Play back audio detections
• Print out detection information
• Save detections
• Save whole audio stream
• Plot detections

API Reference

• Core
  • auditok.core.load
  • auditok.core.split
  • auditok.core.AudioRegion
  • auditok.core.StreamTokenizer
• Util
  • auditok.util.AudioEnergyValidator
  • auditok.util.AudioReader
  • auditok.util.Recorder
  • auditok.util.make_duration_formatter
  • auditok.util.make_channel_selector
• Low-level IO
  • auditok.io.AudioSource
  • auditok.io.Rewindable
  • auditok.io.BufferAudioSource
  • auditok.io.WaveAudioSource
  • auditok.io.PyAudioSource
  • auditok.io.StdinAudioSource
  • auditok.io.PyAudioPlayer
  • auditok.io.from_file
  • auditok.io.to_file
  • auditok.io.player_for
• Signal processing
  • auditok.signal.to_array
  • auditok.signal.extract_single_channel
  • auditok.signal.compute_average_channel
  • auditok.signal.compute_average_channel_stereo
  • auditok.signal.separate_channels
  • auditok.signal.calculate_energy_single_channel
  • auditok.signal.calculate_energy_multichannel
• Dataset
  • auditok.dataset.one_to_six_arabic_16000_mono_bc_noise
  • auditok.dataset.was_der_mensch_saet_mono_44100_lead_trail_silence

License

MIT.