| """Interpolate f0 through unvoiced frames exactly as training did. |
| |
| The conformer's `f0_key` is `f0_interp`, which is pYAAPT's own interpolation |
| of the raw pitch track -- not a straight line through the gap. It median |
| filters, fits a shape-preserving PCHIP spline over the voiced frames, fills |
| the zeros from that, median filters again, and extends the first and last |
| voiced values outward. |
| |
| Nothing here reimplements any of that. The real `pYAAPT.PitchObj` is used, |
| with the same monkey-patch the training pipeline applies, so every constant |
| and helper comes from the library rather than from a copy that can drift. |
| |
| This is for contours built here -- drawn strokes with gaps where the pen was |
| lifted. It cannot reproduce a stored `f0_interp` from a stored raw `f0`: the |
| training pipeline interpolates first and *then* truncates (`f0 = f0[6:]`, |
| then both arrays cut to the shorter), so the original interpolation saw |
| neighbouring frames that no longer exist. Differences of up to ~14 Hz appear |
| at the end of the contour for exactly that reason. Where a stored |
| `f0_interp` exists, use it rather than recomputing. |
| """ |
|
|
| from __future__ import annotations |
|
|
| import numpy as np |
|
|
|
|
| def _blank_pitch_obj(f0: np.ndarray): |
| """A real PitchObj carrying `f0`, without running pitch tracking on audio. |
| |
| PitchObj.__init__ wants a SignalObj to analyse. Interpolation only reads |
| `samp_values` and `nframes` (plus class constants and `edges_finder`), so |
| the object is built uninitialised and those two fields are set directly -- |
| every other attribute and method is the library's own. |
| """ |
| from amfm_decompy import pYAAPT |
|
|
| obj = pYAAPT.PitchObj.__new__(pYAAPT.PitchObj) |
| obj.samp_values = np.asarray(f0, dtype=np.float64) |
| obj.nframes = len(obj.samp_values) |
| return obj |
|
|
|
|
| def interpolate_f0(f0: np.ndarray) -> np.ndarray: |
| """Raw f0 (zeros at unvoiced frames) -> the contour the model expects. |
| |
| Returns the input unchanged when there is nothing to interpolate. |
| """ |
| f0 = np.asarray(f0, dtype=np.float64) |
| if f0.size == 0: |
| return f0 |
| if not (f0 == 0).any(): |
| return f0 |
|
|
| from ._yaapt_patch import patched_interpolate |
|
|
| obj = _blank_pitch_obj(f0) |
| patched_interpolate(obj) |
| return np.asarray(obj.samp_interp, dtype=np.float64) |
|
|
