Hugging Face's logo

okestro-ai-lab
/
FastSLM-ASR

Audio-Text-to-Text
Transformers
Safetensors
English
Korean
fastslm
feature-extraction
audio
text-generation
custom_code
Eval Results
Model card Files
xet
 Community
1
FastSLM-ASR
File size: 2,576 Bytes
e5422ca
 
16bcb34
e5422ca
 
 
16bcb34
e5422ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
808eb4b
 
 
 
e5422ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16bcb34
64cb5b8
f23ccdf
16bcb34
 
64cb5b8
e5422ca
 
808eb4b
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
{
  "architectures": [
    "FastSLMForConditionalGeneration"
  ],
  "encoder_config": {
    "compression_size": 50,
    "model_type": "fastslm_speech_encoder",
    "n_ctx": 1500,
    "n_head": 20,
    "n_layer": 32,
    "n_mels": 128,
    "n_state": 1280,
    "stage_tokens": [
      80,
      80,
      80
    ]
  },
  "llm_config": {
    "_name_or_path": "Qwen/Qwen3-4B",
    "architectures": [
      "Qwen3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2560,
    "initializer_range": 0.02,
    "intermediate_size": 9728,
    "layer_types": [
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 40960,
    "max_window_layers": 36,
    "model_type": "qwen3",
    "num_attention_heads": 32,
    "num_hidden_layers": 36,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_parameters": {
      "rope_type": "default",
      "rope_theta": 1000000
    },
    "sliding_window": null,
    "tie_word_embeddings": true,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151936
  },
  "llm_modules": [
    "q_proj",
    "k_proj",
    "v_proj",
    "o_proj",
    "gate_proj",
    "up_proj",
    "down_proj"
  ],
  "lora_a": 64,
  "lora_r": 16,
  "low_resource": false,
  "model_type": "fastslm",
  "auto_map": {
    "AutoConfig": "configuration_fastslm.FastSLMConfig",
    "AutoModel": "modeling_fastslm.FastSLMForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_fastslm.FastSLMForConditionalGeneration"
  },
  "torch_dtype": "float32",
  "transformers_version": "4.53.1"
}