Feature Extraction
Transformers
Safetensors
English
custom_model
multi-modal
conversational
speechllm
speech2text
custom_code
File size: 300 Bytes
cbfb08a
f4b700f
 
 
cbfb08a
 
f4b700f
 
cbfb08a
 
 
f4b700f
cbfb08a
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
{
  "architectures": [
    "SpeechLLMModel"
  ],
  "audio_enc_dim": 1280,
  "auto_map": {
    "AutoConfig": "config.SpeechLLMModelConfig",
    "AutoModel": "model.SpeechLLMModel"
  },
  "llm_dim": 2048,
  "model_type": "custom_model",
  "torch_dtype": "float32",
  "transformers_version": "4.38.2"
}