quyanh commited on
Commit
8b0bca1
·
verified ·
1 Parent(s): 6a5a373

Training in progress, step 1500

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<asr_text>": 151704,
6
+ "<blank10>": 151686,
7
+ "<blank11>": 151687,
8
+ "<blank12>": 151688,
9
+ "<blank13>": 151689,
10
+ "<blank14>": 151690,
11
+ "<blank15>": 151691,
12
+ "<blank16>": 151692,
13
+ "<blank17>": 151693,
14
+ "<blank18>": 151694,
15
+ "<blank19>": 151695,
16
+ "<blank1>": 151677,
17
+ "<blank20>": 151696,
18
+ "<blank21>": 151697,
19
+ "<blank22>": 151698,
20
+ "<blank23>": 151699,
21
+ "<blank24>": 151700,
22
+ "<blank25>": 151701,
23
+ "<blank26>": 151702,
24
+ "<blank27>": 151703,
25
+ "<blank2>": 151678,
26
+ "<blank3>": 151679,
27
+ "<blank4>": 151680,
28
+ "<blank5>": 151681,
29
+ "<blank6>": 151682,
30
+ "<blank7>": 151683,
31
+ "<blank8>": 151684,
32
+ "<blank9>": 151685,
33
+ "<non_speech>": 151675,
34
+ "<think>": 151667,
35
+ "<tool_call>": 151657,
36
+ "<tool_response>": 151665,
37
+ "<tts_pad>": 151671,
38
+ "<tts_text_bos>": 151672,
39
+ "<tts_text_bos_single>": 151674,
40
+ "<tts_text_eod>": 151673,
41
+ "<|audio_end|>": 151670,
42
+ "<|audio_pad|>": 151676,
43
+ "<|audio_start|>": 151669,
44
+ "<|box_end|>": 151649,
45
+ "<|box_start|>": 151648,
46
+ "<|endoftext|>": 151643,
47
+ "<|file_sep|>": 151664,
48
+ "<|fim_middle|>": 151660,
49
+ "<|fim_pad|>": 151662,
50
+ "<|fim_prefix|>": 151659,
51
+ "<|fim_suffix|>": 151661,
52
+ "<|im_end|>": 151645,
53
+ "<|im_start|>": 151644,
54
+ "<|image_pad|>": 151655,
55
+ "<|object_ref_end|>": 151647,
56
+ "<|object_ref_start|>": 151646,
57
+ "<|quad_end|>": 151651,
58
+ "<|quad_start|>": 151650,
59
+ "<|repo_name|>": 151663,
60
+ "<|video_pad|>": 151656,
61
+ "<|vision_end|>": 151653,
62
+ "<|vision_pad|>": 151654,
63
+ "<|vision_start|>": 151652
64
+ }
config.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ASRForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 151645,
7
+ "model_type": "qwen3_asr",
8
+ "pad_token_id": 151643,
9
+ "support_languages": [
10
+ "Chinese",
11
+ "English",
12
+ "Cantonese",
13
+ "Arabic",
14
+ "German",
15
+ "French",
16
+ "Spanish",
17
+ "Portuguese",
18
+ "Indonesian",
19
+ "Italian",
20
+ "Korean",
21
+ "Russian",
22
+ "Thai",
23
+ "Vietnamese",
24
+ "Japanese",
25
+ "Turkish",
26
+ "Hindi",
27
+ "Malay",
28
+ "Dutch",
29
+ "Swedish",
30
+ "Danish",
31
+ "Finnish",
32
+ "Polish",
33
+ "Czech",
34
+ "Filipino",
35
+ "Persian",
36
+ "Greek",
37
+ "Romanian",
38
+ "Hungarian",
39
+ "Macedonian"
40
+ ],
41
+ "thinker_config": {
42
+ "architectures": [
43
+ "Qwen3ASRForConditionalGeneration"
44
+ ],
45
+ "audio_config": {
46
+ "_name_or_path": "",
47
+ "activation_dropout": 0,
48
+ "activation_function": "gelu",
49
+ "add_cross_attention": false,
50
+ "architectures": null,
51
+ "attention_dropout": 0,
52
+ "bad_words_ids": null,
53
+ "begin_suppress_tokens": null,
54
+ "bos_token_id": null,
55
+ "chunk_size_feed_forward": 0,
56
+ "conv_chunksize": 500,
57
+ "cross_attention_hidden_size": null,
58
+ "d_model": 896,
59
+ "decoder_start_token_id": null,
60
+ "diversity_penalty": 0.0,
61
+ "do_sample": false,
62
+ "downsample_hidden_size": 480,
63
+ "dropout": 0,
64
+ "dtype": null,
65
+ "early_stopping": false,
66
+ "encoder_attention_heads": 14,
67
+ "encoder_ffn_dim": 3584,
68
+ "encoder_layers": 18,
69
+ "encoder_no_repeat_ngram_size": 0,
70
+ "eos_token_id": null,
71
+ "exponential_decay_length_penalty": null,
72
+ "finetuning_task": null,
73
+ "forced_bos_token_id": null,
74
+ "forced_eos_token_id": null,
75
+ "id2label": {
76
+ "0": "LABEL_0",
77
+ "1": "LABEL_1"
78
+ },
79
+ "initializer_range": 0.02,
80
+ "is_decoder": false,
81
+ "is_encoder_decoder": false,
82
+ "label2id": {
83
+ "LABEL_0": 0,
84
+ "LABEL_1": 1
85
+ },
86
+ "length_penalty": 1.0,
87
+ "max_length": 20,
88
+ "max_source_positions": 1500,
89
+ "min_length": 0,
90
+ "model_type": "qwen3_asr_audio_encoder",
91
+ "n_window": 50,
92
+ "n_window_infer": 800,
93
+ "no_repeat_ngram_size": 0,
94
+ "num_beam_groups": 1,
95
+ "num_beams": 1,
96
+ "num_hidden_layers": 18,
97
+ "num_mel_bins": 128,
98
+ "num_return_sequences": 1,
99
+ "output_attentions": false,
100
+ "output_dim": 1024,
101
+ "output_hidden_states": false,
102
+ "output_scores": false,
103
+ "pad_token_id": null,
104
+ "prefix": null,
105
+ "problem_type": null,
106
+ "pruned_heads": {},
107
+ "remove_invalid_values": false,
108
+ "repetition_penalty": 1.0,
109
+ "return_dict": true,
110
+ "return_dict_in_generate": false,
111
+ "scale_embedding": false,
112
+ "sep_token_id": null,
113
+ "suppress_tokens": null,
114
+ "task_specific_params": null,
115
+ "temperature": 1.0,
116
+ "tf_legacy_loss": false,
117
+ "tie_encoder_decoder": false,
118
+ "tie_word_embeddings": true,
119
+ "tokenizer_class": null,
120
+ "top_k": 50,
121
+ "top_p": 1.0,
122
+ "torchscript": false,
123
+ "typical_p": 1.0,
124
+ "use_bfloat16": false
125
+ },
126
+ "audio_end_token_id": 151670,
127
+ "audio_start_token_id": 151669,
128
+ "audio_token_id": 151676,
129
+ "dtype": "bfloat16",
130
+ "initializer_range": 0.02,
131
+ "model_type": "qwen3_asr_thinker",
132
+ "text_config": {
133
+ "_name_or_path": "",
134
+ "add_cross_attention": false,
135
+ "architectures": null,
136
+ "attention_bias": false,
137
+ "attention_dropout": 0.0,
138
+ "bad_words_ids": null,
139
+ "begin_suppress_tokens": null,
140
+ "bos_token_id": null,
141
+ "chunk_size_feed_forward": 0,
142
+ "cross_attention_hidden_size": null,
143
+ "decoder_start_token_id": null,
144
+ "diversity_penalty": 0.0,
145
+ "do_sample": false,
146
+ "dtype": null,
147
+ "early_stopping": false,
148
+ "encoder_no_repeat_ngram_size": 0,
149
+ "eos_token_id": null,
150
+ "exponential_decay_length_penalty": null,
151
+ "finetuning_task": null,
152
+ "forced_bos_token_id": null,
153
+ "forced_eos_token_id": null,
154
+ "head_dim": 128,
155
+ "hidden_act": "silu",
156
+ "hidden_size": 1024,
157
+ "id2label": {
158
+ "0": "LABEL_0",
159
+ "1": "LABEL_1"
160
+ },
161
+ "initializer_range": 0.02,
162
+ "intermediate_size": 3072,
163
+ "is_decoder": false,
164
+ "is_encoder_decoder": false,
165
+ "label2id": {
166
+ "LABEL_0": 0,
167
+ "LABEL_1": 1
168
+ },
169
+ "length_penalty": 1.0,
170
+ "max_length": 20,
171
+ "max_position_embeddings": 65536,
172
+ "min_length": 0,
173
+ "model_type": "qwen3_asr_text",
174
+ "no_repeat_ngram_size": 0,
175
+ "num_attention_heads": 16,
176
+ "num_beam_groups": 1,
177
+ "num_beams": 1,
178
+ "num_hidden_layers": 28,
179
+ "num_key_value_heads": 8,
180
+ "num_return_sequences": 1,
181
+ "output_attentions": false,
182
+ "output_hidden_states": false,
183
+ "output_scores": false,
184
+ "pad_token_id": null,
185
+ "prefix": null,
186
+ "problem_type": null,
187
+ "pruned_heads": {},
188
+ "remove_invalid_values": false,
189
+ "repetition_penalty": 1.0,
190
+ "return_dict": true,
191
+ "return_dict_in_generate": false,
192
+ "rms_norm_eps": 1e-06,
193
+ "rope_scaling": {
194
+ "interleaved": true,
195
+ "mrope_interleaved": true,
196
+ "mrope_section": [
197
+ 24,
198
+ 20,
199
+ 20
200
+ ],
201
+ "rope_type": "default",
202
+ "type": "default"
203
+ },
204
+ "rope_theta": 1000000,
205
+ "sep_token_id": null,
206
+ "suppress_tokens": null,
207
+ "task_specific_params": null,
208
+ "temperature": 1.0,
209
+ "tf_legacy_loss": false,
210
+ "tie_encoder_decoder": false,
211
+ "tie_word_embeddings": true,
212
+ "tokenizer_class": null,
213
+ "top_k": 50,
214
+ "top_p": 1.0,
215
+ "torchscript": false,
216
+ "typical_p": 1.0,
217
+ "use_bfloat16": false,
218
+ "use_cache": true,
219
+ "vocab_size": 151936
220
+ },
221
+ "user_token_id": 872
222
+ },
223
+ "transformers_version": "4.57.6"
224
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151645
5
+ ],
6
+ "pad_token_id": 151643,
7
+ "transformers_version": "4.57.6"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b7f4c10733340ce05bae9f4fa62cdb6b7d5452333540101d9574ce81989cbc
3
+ size 1564926456
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>",
16
+ "<|audio_start|>",
17
+ "<|audio_end|>",
18
+ "<tts_pad>",
19
+ "<tts_text_bos>",
20
+ "<tts_text_bos_single>",
21
+ "<|audio_pad|>"
22
+ ],
23
+ "audio_bos_token": "<|audio_start|>",
24
+ "audio_eos_token": "<|audio_end|>",
25
+ "audio_token": "<|audio_pad|>",
26
+ "eos_token": {
27
+ "content": "<|im_end|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "image_token": "<|image_pad|>",
34
+ "pad_token": {
35
+ "content": "<|endoftext|>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "video_token": "<|video_pad|>",
42
+ "vision_bos_token": "<|vision_start|>",
43
+ "vision_eos_token": "<|vision_end|>"
44
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd2a97b55c8f7f9c328c73ee9b9178771037e9f566dfca8e238a063d41cbac92
3
+ size 11429377
tokenizer_config.json ADDED
@@ -0,0 +1,550 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151669": {
214
+ "content": "<|audio_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|audio_end|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<tts_pad>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<tts_text_bos>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<tts_text_eod>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<tts_text_bos_single>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<non_speech>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "151676": {
270
+ "content": "<|audio_pad|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "<blank1>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<blank2>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "<blank3>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<blank4>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151681": {
310
+ "content": "<blank5>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151682": {
318
+ "content": "<blank6>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151683": {
326
+ "content": "<blank7>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151684": {
334
+ "content": "<blank8>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151685": {
342
+ "content": "<blank9>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151686": {
350
+ "content": "<blank10>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151687": {
358
+ "content": "<blank11>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151688": {
366
+ "content": "<blank12>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151689": {
374
+ "content": "<blank13>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151690": {
382
+ "content": "<blank14>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151691": {
390
+ "content": "<blank15>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151692": {
398
+ "content": "<blank16>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151693": {
406
+ "content": "<blank17>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151694": {
414
+ "content": "<blank18>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151695": {
422
+ "content": "<blank19>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151696": {
430
+ "content": "<blank20>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151697": {
438
+ "content": "<blank21>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151698": {
446
+ "content": "<blank22>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151699": {
454
+ "content": "<blank23>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151700": {
462
+ "content": "<blank24>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "151701": {
470
+ "content": "<blank25>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "151702": {
478
+ "content": "<blank26>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "151703": {
486
+ "content": "<blank27>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "151704": {
494
+ "content": "<asr_text>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ }
501
+ },
502
+ "additional_special_tokens": [
503
+ "<|im_start|>",
504
+ "<|im_end|>",
505
+ "<|object_ref_start|>",
506
+ "<|object_ref_end|>",
507
+ "<|box_start|>",
508
+ "<|box_end|>",
509
+ "<|quad_start|>",
510
+ "<|quad_end|>",
511
+ "<|vision_start|>",
512
+ "<|vision_end|>",
513
+ "<|vision_pad|>",
514
+ "<|image_pad|>",
515
+ "<|video_pad|>",
516
+ "<|audio_start|>",
517
+ "<|audio_end|>",
518
+ "<tts_pad>",
519
+ "<tts_text_bos>",
520
+ "<tts_text_bos_single>",
521
+ "<|audio_pad|>"
522
+ ],
523
+ "audio_bos_token": "<|audio_start|>",
524
+ "audio_eos_token": "<|audio_end|>",
525
+ "audio_token": "<|audio_pad|>",
526
+ "bos_token": null,
527
+ "clean_up_tokenization_spaces": false,
528
+ "eos_token": "<|im_end|>",
529
+ "errors": "replace",
530
+ "extra_special_tokens": {
531
+ "audio_bos_token": "<|audio_start|>",
532
+ "audio_eos_token": "<|audio_end|>",
533
+ "audio_token": "<|audio_pad|>",
534
+ "image_token": "<|image_pad|>",
535
+ "video_token": "<|video_pad|>",
536
+ "vision_bos_token": "<|vision_start|>",
537
+ "vision_eos_token": "<|vision_end|>"
538
+ },
539
+ "fix_mistral_regex": true,
540
+ "image_token": "<|image_pad|>",
541
+ "model_max_length": 131072,
542
+ "pad_token": "<|endoftext|>",
543
+ "processor_class": "Qwen3ASRProcessor",
544
+ "split_special_tokens": false,
545
+ "tokenizer_class": "Qwen2Tokenizer",
546
+ "unk_token": null,
547
+ "video_token": "<|video_pad|>",
548
+ "vision_bos_token": "<|vision_start|>",
549
+ "vision_eos_token": "<|vision_end|>"
550
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6d16b60911be0e76eba04187dc913d9506390d0b827141c02d2692c4059613c
3
+ size 5905
vocab.json ADDED
The diff for this file is too large to render. See raw diff