Feature Extraction
Transformers
Safetensors
English
custom_model
multi-modal
conversational
speechllm
speech2text
custom_code
File size: 300 Bytes
cbfb08a
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
from transformers import PretrainedConfig

class CustomModelConfig(PretrainedConfig):
    model_type = "custom_model"
    
    def __init__(self, audio_enc_dim=1280, llm_dim=2048, **kwargs):
        super().__init__(**kwargs)
        self.audio_enc_dim = audio_enc_dim
        self.llm_dim = llm_dim