zhifu gao
2024-04-24 861147c7308b91068ffa02724fdf74ee623a909e
funasr/models/llm_asr/adaptor.py
@@ -3,6 +3,7 @@
from funasr.register import tables
@tables.register("adaptor_classes", "Linear")
class Linear(nn.Module):
    def __init__(self, downsample_rate, encoder_dim, llm_dim, ffn_dim: int = 2048, **kwargs):
@@ -28,6 +29,7 @@
        x = self.linear2(x)
        return x
@tables.register("adaptor_classes", "QFormer")
class EncoderProjectorQFormer(nn.Module):
    def __init__(self, downsample_rate, encoder_dim, llm_dim, ffn_dim: int = 2048, **kwargs):
@@ -35,6 +37,7 @@
        self.encoder_dim = encoder_dim
        self.llm_dim = llm_dim
        from transformers import Blip2QFormerConfig, Blip2QFormerModel
        configuration = Blip2QFormerConfig()
        configuration.encoder_hidden_size = self.encoder_dim
        configuration.num_hidden_layers = 2