librosax.feature.chroma_cqt

chroma_cqt(*, y: Array | None = None, sr: float = 22050, C: Array | None = None, hop_length: int = 512, fmin: float | None = None, norm: str | float | None = inf, threshold: float = 0.0, tuning: float | None = 0.0, n_chroma: int = 12, n_octaves: int = 7, window: Array | None = None, bins_per_octave: int = 36, cqt_mode: str = 'full', **kwargs) → Array[source]

Chromagram from a constant-Q transform.

Parameters:

  • y –

    Audio time series. The last axis must be time.

    • (T,) - single waveform

    • (B, T) - batch of waveforms

  • sr – Sampling rate

  • C – Pre-computed CQT spectrogram with shape (..., n_cqt_bins, N)

  • hop_length – Number of samples between successive CQT columns

  • fmin – Minimum frequency. Default: C1 ~= 32.70 Hz

  • norm – Normalization mode for chroma

  • threshold – Pre-normalization energy threshold

  • tuning – Tuning deviation from A440 in fractional bins

  • n_chroma – Number of chroma bins to produce

  • n_octaves – Number of octaves to analyze above fmin

  • window – Optional weighting window

  • bins_per_octave – Number of bins per octave in the CQT

  • cqt_mode – CQT mode (‘full’ or ‘hybrid’)

  • **kwargs – Additional parameters for cqt

Returns:

Chromagram with shape (..., n_chroma, N).

  • (T,) → (n_chroma, N)

  • (B, T) → (B, n_chroma, N)