| """pYAAPT's f0 interpolation, with the fix the training pipeline applies. |
| |
| Copied verbatim from `precompute_prosody._patched_interpolate` in the |
| prosody_embeddings_to_mel repo. Stock pYAAPT mishandles extrapolation before |
| the first and after the last voiced frame, which can flatten the entire |
| contour; the preprocessor the training pipeline replaced monkey-patches this |
| in, so f0_interp only matches the offline pipeline with the same patch. |
| |
| Kept as a verbatim copy rather than an import because that repo's module |
| pulls in a submodule that is not checked out. If the original changes, this |
| must be re-copied. |
| """ |
|
|
| from __future__ import annotations |
|
|
|
|
| def patched_interpolate(self): |
| """pYAAPT.PitchObj.interpolate with the MU-NLPC fix, copied verbatim. |
| |
| Stock pYAAPT mishandles extrapolation before the first and after the last |
| voiced frame, which can flatten the entire f0 contour. The preprocessor we |
| are replacing monkey-patches this in, so f0_interp only matches the offline |
| pipeline's if the same patch is applied here. |
| """ |
| import numpy as _np |
| from scipy import interpolate as scipy_interp |
| from scipy.signal import medfilt |
|
|
| pitch = _np.zeros((self.nframes)) |
| pitch[:] = self.samp_values |
| pitch2 = medfilt(self.samp_values, self.SMOOTH_FACTOR) |
|
|
| edges = self.edges_finder(pitch) |
| first_sample = pitch[0] |
| last_sample = pitch[-1] |
|
|
| if len(_np.nonzero(pitch2)[0]) < 2: |
| pitch[pitch == 0] = self.PTCH_TYP |
| else: |
| nz_pitch = pitch2[pitch2 > 0] |
| pitch2 = scipy_interp.pchip(_np.nonzero(pitch2)[0], |
| nz_pitch)(range(self.nframes)) |
| pitch[pitch == 0] = pitch2[pitch == 0] |
| if self.SMOOTH > 0: |
| pitch = medfilt(pitch, self.SMOOTH_FACTOR) |
| try: |
| if first_sample == 0: |
| if edges[0] == 0: |
| edges[0] = 1 |
| pitch[:edges[0] - 1] = pitch[edges[0]] |
| if last_sample == 0: |
| pitch[edges[-1] + 1:] = pitch[edges[-1]] |
| except Exception: |
| pass |
| self.samp_interp = pitch |
|
|
