This commit is contained in:
Eren G??lge 2022-05-17 13:34:38 +02:00
parent a05c82f9ef
commit c437db15fd
2 changed files with 1 additions and 5 deletions

View File

@ -9,7 +9,7 @@ from scipy import signal
from TTS.encoder.models.lstm import LSTMSpeakerEncoder
from TTS.encoder.models.resnet import ResNetSpeakerEncoder
from TTS.utils.io import save_fsspec
from trainer.io import save_fsspec
class AugmentWAV(object):

View File

@ -13,7 +13,6 @@ def split_dataset(items, eval_split_max_size=None, eval_split_size=0.01):
"""Split a dataset into train and eval. Consider speaker distribution in multi-speaker training.
Args:
<<<<<<< HEAD
items (List[List]):
A list of samples. Each sample is a list of `[audio_path, text, speaker_id]`.
@ -23,9 +22,6 @@ def split_dataset(items, eval_split_max_size=None, eval_split_size=0.01):
eval_split_size (float):
If between 0.0 and 1.0 represents the proportion of the dataset to include in the evaluation set.
If > 1, represents the absolute number of evaluation samples. Defaults to 0.01 (1%).
=======
items (List[List]): A list of samples. Each sample is a list of `[text, audio_path, speaker_id]`.
>>>>>>> Fix docstring
"""
speakers = [item["speaker_name"] for item in items]
is_multi_speaker = len(set(speakers)) > 1