mirror of
https://github.com/liuhaozhe6788/voice-cloning-collab.git
synced 2025-12-16 19:58:01 +01:00
29 lines
985 B
Python
29 lines
985 B
Python
import numpy as np
|
|
|
|
|
|
class Utterance:
|
|
def __init__(self, frames_fpath, wave_fpath):
|
|
self.frames_fpath = frames_fpath
|
|
self.wave_fpath = wave_fpath
|
|
|
|
def get_frames(self):
|
|
# frame_len = len(np.load(self.frames_fpath))
|
|
return np.load(self.frames_fpath)
|
|
|
|
def random_partial(self, n_frames):
|
|
"""
|
|
Crops the frames into a partial utterance of n_frames
|
|
|
|
:param n_frames: The number of frames of the partial utterance
|
|
:return: the partial utterance frames and a tuple indicating the start and end of the
|
|
partial utterance in the complete utterance.
|
|
"""
|
|
frames = self.get_frames()
|
|
if frames.shape[0] == n_frames:
|
|
start = 0
|
|
else:
|
|
start = np.random.randint(0, frames.shape[0] - n_frames)
|
|
end = start + n_frames
|
|
# frame_len = end - start
|
|
# frames_trim = frames[start:end]
|
|
return frames[start:end], (start, end) |