Safetensors
qwen3_asr
Wendy9805 commited on
Commit
6db2fde
·
verified ·
1 Parent(s): 2cd78d0

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +222 -0
config.json ADDED
@@ -0,0 +1,222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ASRForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "model_type": "qwen3_asr",
7
+ "support_languages": [
8
+ "Chinese",
9
+ "English",
10
+ "Cantonese",
11
+ "Arabic",
12
+ "German",
13
+ "French",
14
+ "Spanish",
15
+ "Portuguese",
16
+ "Indonesian",
17
+ "Italian",
18
+ "Korean",
19
+ "Russian",
20
+ "Thai",
21
+ "Vietnamese",
22
+ "Japanese",
23
+ "Turkish",
24
+ "Hindi",
25
+ "Malay",
26
+ "Dutch",
27
+ "Swedish",
28
+ "Danish",
29
+ "Finnish",
30
+ "Polish",
31
+ "Czech",
32
+ "Filipino",
33
+ "Persian",
34
+ "Greek",
35
+ "Romanian",
36
+ "Hungarian",
37
+ "Macedonian"
38
+ ],
39
+ "thinker_config": {
40
+ "architectures": [
41
+ "Qwen3ASRForConditionalGeneration"
42
+ ],
43
+ "audio_config": {
44
+ "_name_or_path": "",
45
+ "activation_dropout": 0,
46
+ "activation_function": "gelu",
47
+ "add_cross_attention": false,
48
+ "architectures": null,
49
+ "attention_dropout": 0,
50
+ "bad_words_ids": null,
51
+ "begin_suppress_tokens": null,
52
+ "bos_token_id": null,
53
+ "chunk_size_feed_forward": 0,
54
+ "conv_chunksize": 500,
55
+ "cross_attention_hidden_size": null,
56
+ "d_model": 1024,
57
+ "decoder_start_token_id": null,
58
+ "diversity_penalty": 0.0,
59
+ "do_sample": false,
60
+ "downsample_hidden_size": 480,
61
+ "dropout": 0,
62
+ "dtype": null,
63
+ "early_stopping": false,
64
+ "encoder_attention_heads": 16,
65
+ "encoder_ffn_dim": 4096,
66
+ "encoder_layers": 24,
67
+ "encoder_no_repeat_ngram_size": 0,
68
+ "eos_token_id": null,
69
+ "exponential_decay_length_penalty": null,
70
+ "finetuning_task": null,
71
+ "forced_bos_token_id": null,
72
+ "forced_eos_token_id": null,
73
+ "id2label": {
74
+ "0": "LABEL_0",
75
+ "1": "LABEL_1"
76
+ },
77
+ "initializer_range": 0.02,
78
+ "is_decoder": false,
79
+ "is_encoder_decoder": false,
80
+ "label2id": {
81
+ "LABEL_0": 0,
82
+ "LABEL_1": 1
83
+ },
84
+ "length_penalty": 1.0,
85
+ "max_length": 20,
86
+ "max_source_positions": 1500,
87
+ "min_length": 0,
88
+ "model_type": "qwen3_asr_audio_encoder",
89
+ "n_window": 50,
90
+ "n_window_infer": 800,
91
+ "no_repeat_ngram_size": 0,
92
+ "num_beam_groups": 1,
93
+ "num_beams": 1,
94
+ "num_hidden_layers": 24,
95
+ "num_mel_bins": 128,
96
+ "num_return_sequences": 1,
97
+ "output_attentions": false,
98
+ "output_dim": 2048,
99
+ "output_hidden_states": false,
100
+ "output_scores": false,
101
+ "pad_token_id": null,
102
+ "prefix": null,
103
+ "problem_type": null,
104
+ "pruned_heads": {},
105
+ "remove_invalid_values": false,
106
+ "repetition_penalty": 1.0,
107
+ "return_dict": true,
108
+ "return_dict_in_generate": false,
109
+ "scale_embedding": false,
110
+ "sep_token_id": null,
111
+ "suppress_tokens": null,
112
+ "task_specific_params": null,
113
+ "temperature": 1.0,
114
+ "tf_legacy_loss": false,
115
+ "tie_encoder_decoder": false,
116
+ "tie_word_embeddings": true,
117
+ "tokenizer_class": null,
118
+ "top_k": 50,
119
+ "top_p": 1.0,
120
+ "torchscript": false,
121
+ "typical_p": 1.0,
122
+ "use_bfloat16": false
123
+ },
124
+ "audio_end_token_id": 151670,
125
+ "audio_start_token_id": 151669,
126
+ "audio_token_id": 151676,
127
+ "dtype": "bfloat16",
128
+ "initializer_range": 0.02,
129
+ "model_type": "qwen3_asr_thinker",
130
+ "text_config": {
131
+ "_name_or_path": "",
132
+ "add_cross_attention": false,
133
+ "architectures": null,
134
+ "attention_bias": false,
135
+ "attention_dropout": 0.0,
136
+ "bad_words_ids": null,
137
+ "begin_suppress_tokens": null,
138
+ "bos_token_id": null,
139
+ "chunk_size_feed_forward": 0,
140
+ "cross_attention_hidden_size": null,
141
+ "decoder_start_token_id": null,
142
+ "diversity_penalty": 0.0,
143
+ "do_sample": false,
144
+ "dtype": null,
145
+ "early_stopping": false,
146
+ "encoder_no_repeat_ngram_size": 0,
147
+ "eos_token_id": null,
148
+ "exponential_decay_length_penalty": null,
149
+ "finetuning_task": null,
150
+ "forced_bos_token_id": null,
151
+ "forced_eos_token_id": null,
152
+ "head_dim": 128,
153
+ "hidden_act": "silu",
154
+ "hidden_size": 2048,
155
+ "id2label": {
156
+ "0": "LABEL_0",
157
+ "1": "LABEL_1"
158
+ },
159
+ "initializer_range": 0.02,
160
+ "intermediate_size": 6144,
161
+ "is_decoder": false,
162
+ "is_encoder_decoder": false,
163
+ "label2id": {
164
+ "LABEL_0": 0,
165
+ "LABEL_1": 1
166
+ },
167
+ "length_penalty": 1.0,
168
+ "max_length": 20,
169
+ "max_position_embeddings": 65536,
170
+ "min_length": 0,
171
+ "model_type": "qwen3_asr_text",
172
+ "no_repeat_ngram_size": 0,
173
+ "num_attention_heads": 16,
174
+ "num_beam_groups": 1,
175
+ "num_beams": 1,
176
+ "num_hidden_layers": 28,
177
+ "num_key_value_heads": 8,
178
+ "num_return_sequences": 1,
179
+ "output_attentions": false,
180
+ "output_hidden_states": false,
181
+ "output_scores": false,
182
+ "pad_token_id": null,
183
+ "prefix": null,
184
+ "problem_type": null,
185
+ "pruned_heads": {},
186
+ "remove_invalid_values": false,
187
+ "repetition_penalty": 1.0,
188
+ "return_dict": true,
189
+ "return_dict_in_generate": false,
190
+ "rms_norm_eps": 1e-06,
191
+ "rope_scaling": {
192
+ "interleaved": true,
193
+ "mrope_interleaved": true,
194
+ "mrope_section": [
195
+ 24,
196
+ 20,
197
+ 20
198
+ ],
199
+ "rope_type": "default",
200
+ "type": "default"
201
+ },
202
+ "rope_theta": 1000000,
203
+ "sep_token_id": null,
204
+ "suppress_tokens": null,
205
+ "task_specific_params": null,
206
+ "temperature": 1.0,
207
+ "tf_legacy_loss": false,
208
+ "tie_encoder_decoder": false,
209
+ "tie_word_embeddings": true,
210
+ "tokenizer_class": null,
211
+ "top_k": 50,
212
+ "top_p": 1.0,
213
+ "torchscript": false,
214
+ "typical_p": 1.0,
215
+ "use_bfloat16": false,
216
+ "use_cache": true,
217
+ "vocab_size": 151936
218
+ },
219
+ "user_token_id": 872
220
+ },
221
+ "transformers_version": "4.57.6"
222
+ }