mirror of
https://github.com/babysor/Realtime-Voice-Clone-Chinese.git
synced 2026-07-05 11:06:16 +08:00
Refactor Project to 3 parts: Models, Control, Data
Need readme
This commit is contained in:
12
models/encoder/data_objects/speaker_batch.py
Normal file
12
models/encoder/data_objects/speaker_batch.py
Normal file
@@ -0,0 +1,12 @@
|
||||
import numpy as np
|
||||
from typing import List
|
||||
from models.encoder.data_objects.speaker import Speaker
|
||||
|
||||
class SpeakerBatch:
|
||||
def __init__(self, speakers: List[Speaker], utterances_per_speaker: int, n_frames: int):
|
||||
self.speakers = speakers
|
||||
self.partials = {s: s.random_partial(utterances_per_speaker, n_frames) for s in speakers}
|
||||
|
||||
# Array of shape (n_speakers * n_utterances, n_frames, mel_n), e.g. for 3 speakers with
|
||||
# 4 utterances each of 160 frames of 40 mel coefficients: (12, 160, 40)
|
||||
self.data = np.array([frames for s in speakers for _, frames, _ in self.partials[s]])
|
||||
Reference in New Issue
Block a user