File size: 582 Bytes
5b70063 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 |
from transformers import PretrainedConfig
from typing import List
class LoCoNetConfig(PretrainedConfig):
model_type = "loconet"
def __init__(
self,
num_speakers: int = 3,
clip_length: int = 200,
av: str = "speaker_temporal",
av_layers: int = 3,
adjust_attention: bool = False,
**kwargs,
):
self.num_speakers = num_speakers
self.clip_length = clip_length
self.av = av
self.av_layers = av_layers
self.adjust_attention = adjust_attention
super().__init__(**kwargs)
|