Feature Extraction
Transformers
Safetensors
diva
custom_code
File size: 3,636 Bytes
547936a
74750ce
d42d04c
547936a
d0dcfb2
547936a
e512cdc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
547936a
 
e512cdc
547936a
 
e512cdc
547936a
e512cdc
 
 
 
 
 
 
 
 
 
547936a
e512cdc
547936a
e512cdc
 
 
 
 
 
 
547936a
e512cdc
547936a
e512cdc
 
 
 
547936a
e512cdc
547936a
 
e512cdc
 
547936a
 
 
 
e512cdc
 
 
547936a
 
 
 
e512cdc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
547936a
e512cdc
547936a
e512cdc
 
 
547936a
e512cdc
 
 
 
 
 
547936a
 
e512cdc
 
547936a
 
e512cdc
 
 
547936a
e512cdc
 
 
 
547936a
e512cdc
 
547936a
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
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
{
  "model_type": "diva",
  "architectures": [ "DiVAModel" ],
  "auto_map": {
    "AutoModel": "modeling_diva.DiVAModel"
  },
  "vocab_size": 128256,
  "decoder": {
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0,
    "bos_token_id": 128000,
    "eos_token_id": 128001,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 8192,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 500000,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.40.0.dev0",
    "use_cache": true,
    "vocab_size": 128256
  },
  "encoder": {
    "_name_or_path": "openai/whisper-large-v3",
    "activation_dropout": 0,
    "activation_function": "gelu",
    "add_cross_attention": false,
    "apply_spec_augment": false,
    "architectures": [
      "WhisperForConditionalGeneration"
    ],
    "attention_dropout": 0,
    "bad_words_ids": null,
    "begin_suppress_tokens": [
      220,
      50257
    ],
    "bos_token_id": 50257,
    "chunk_size_feed_forward": 0,
    "classifier_proj_size": 256,
    "cross_attention_hidden_size": null,
    "d_model": 1280,
    "decoder_attention_heads": 20,
    "decoder_ffn_dim": 5120,
    "decoder_layerdrop": 0,
    "decoder_layers": 32,
    "decoder_start_token_id": 50258,
    "diversity_penalty": 0,
    "do_sample": false,
    "dropout": 0,
    "early_stopping": false,
    "encoder_attention_heads": 20,
    "encoder_ffn_dim": 5120,
    "encoder_layerdrop": 0,
    "encoder_layers": 32,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 50257,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "init_std": 0.02,
    "is_decoder": false,
    "is_encoder_decoder": true,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1,
    "mask_feature_length": 10,
    "mask_feature_min_masks": 0,
    "mask_feature_prob": 0,
    "mask_time_length": 10,
    "mask_time_min_masks": 2,
    "mask_time_prob": 0.05,
    "max_length": 448,
    "max_source_positions": 1500,
    "max_target_positions": 448,
    "median_filter_width": 7,
    "min_length": 0,
    "model_type": "whisper",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 32,
    "num_mel_bins": 128,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 50256,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1,
    "return_dict": true,
    "return_dict_in_generate": false,
    "scale_embedding": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1,
    "torch_dtype": "float16",
    "torchscript": false,
    "transformers_version": "4.38.2",
    "typical_p": 1,
    "use_bfloat16": false,
    "use_cache": true,
    "use_weighted_layer_sum": false,
    "vocab_size": 51866
  },
  "time_dialation": 4,
  "transformers_version": "4.38.2"
}