Options
All
  • Public
  • Public/Protected
  • All
Menu

Class Coconet

Coconet model implementation in TensorflowJS. Thanks to James Wexler for the original implementation.

Hierarchy

  • Coconet

Index

Constructors

Methods

Constructors

constructor

  • new Coconet(checkpointURL: string): Coconet

Methods

dispose

  • dispose(): void

infill

  • infill(sequence: INoteSequence, config?: CoconetConfig): Promise<NoteSequence>

  • Use the model to generate a Bach-style 4-part harmony, conditioned on an input sequence. The notes in the input sequence should have the instrument property set corresponding to which voice the note belongs to: 0 for Soprano, 1 for Alto, 2 for Tenor and 3 for Bass.

    Note: regardless of the length of the notes in the original sequence, all the notes in the generated sequence will be 1 step long. If you want to clean up the sequence to consider consecutive notes for the same pitch and instruments as "held", you can call mergeHeldNotes on the result. This function will replace any of the existing voices with the output of the model. If you want to restore any of the original voices, you can call replaceVoice on the output, specifying which voice should be restored.

    Parameters

    • sequence: INoteSequence

      The sequence to infill. Must be quantized.

    • Optional config: CoconetConfig

      (Optional) Infill parameterers like temperature, the number of sampling iterations, or masks.

    Returns Promise<NoteSequence>

initialize

  • initialize(): Promise<void>

  • Loads variables from the checkpoint and instantiates the model.

    Returns Promise<void>

instantiateFromSpec

  • instantiateFromSpec(): void

isInitialized

  • isInitialized(): boolean

Generated using TypeDoc