hf-transformers-bot commited on
Commit
0faef4c
·
verified ·
1 Parent(s): 6a5ec0b

Add tiny processor fixture for testing

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
chat_template.jinja ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {%- set ns = namespace(system_text='') -%}{%- for m in messages -%}{%- if m.role == 'system' -%}{%- if m.content is string -%}{%- set ns.system_text = ns.system_text + m.content -%}{%- else -%}{%- for c in m.content -%}{%- if c.type == 'text' and (c.text is defined) -%}{%- set ns.system_text = ns.system_text + c.text -%}{%- endif -%}{%- endfor -%}{%- endif -%}{%- endif -%}{%- endfor -%}{%- set ns2 = namespace(audio_tokens='') -%}{%- for m in messages -%}{%- if m.content is not string -%}{%- for c in m.content -%}{%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}{%- set ns2.audio_tokens = ns2.audio_tokens + '<|audio_start|><|audio_pad|><|audio_end|>' -%}{%- endif -%}{%- endfor -%}{%- endif -%}{%- endfor -%}{{- '<|im_start|>system
2
+ ' + ns.system_text + '<|im_end|>
3
+ ' -}}{{- '<|im_start|>user
4
+ ' + ns2.audio_tokens + '<|im_end|>
5
+ ' -}}{%- for m in messages -%}{%- if m.role == 'assistant' -%}{%- set ns3 = namespace(assistant_text='') -%}{%- if m.content is string -%}{%- set ns3.assistant_text = m.content -%}{%- else -%}{%- for c in m.content -%}{%- if c.type == 'text' and (c.text is defined) -%}{%- set ns3.assistant_text = ns3.assistant_text + c.text -%}{%- endif -%}{%- endfor -%}{%- endif -%}{{- '<|im_start|>assistant
6
+ ' -}}{% generation %}{{- ns3.assistant_text + '<|im_end|>
7
+ ' -}}{% endgeneration %}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{- '<|im_start|>assistant
8
+ ' -}}{%- endif -%}
config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ASRForConditionalGeneration"
4
+ ],
5
+ "audio_config": {
6
+ "activation_dropout": 0,
7
+ "activation_function": "gelu",
8
+ "attention_dropout": 0,
9
+ "conv_chunksize": 500,
10
+ "d_model": 896,
11
+ "downsample_hidden_size": 480,
12
+ "dropout": 0,
13
+ "encoder_attention_heads": 14,
14
+ "encoder_ffn_dim": 3584,
15
+ "encoder_layers": 18,
16
+ "initializer_range": 0.02,
17
+ "max_position_embeddings": 13,
18
+ "model_type": "qwen3_asr_encoder",
19
+ "n_window": 50,
20
+ "n_window_infer": 800,
21
+ "num_key_value_heads": 14,
22
+ "num_mel_bins": 128,
23
+ "output_dim": 1024,
24
+ "scale_embedding": false
25
+ },
26
+ "audio_token_id": 151676,
27
+ "dtype": "bfloat16",
28
+ "eos_token_id": [
29
+ 500,
30
+ 502
31
+ ],
32
+ "initializer_range": 0.02,
33
+ "model_type": "qwen3_asr",
34
+ "pad_token_id": 502,
35
+ "text_config": {
36
+ "attention_bias": false,
37
+ "attention_dropout": 0.0,
38
+ "bos_token_id": null,
39
+ "eos_token_id": null,
40
+ "head_dim": 128,
41
+ "hidden_act": "silu",
42
+ "hidden_size": 1024,
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
+ "layer_types": [
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention"
74
+ ],
75
+ "max_position_embeddings": 65536,
76
+ "max_window_layers": 28,
77
+ "model_type": "qwen3",
78
+ "num_attention_heads": 16,
79
+ "num_hidden_layers": 28,
80
+ "num_key_value_heads": 8,
81
+ "pad_token_id": null,
82
+ "rms_norm_eps": 1e-06,
83
+ "rope_parameters": {
84
+ "rope_theta": 1000000,
85
+ "rope_type": "default"
86
+ },
87
+ "sliding_window": null,
88
+ "tie_word_embeddings": true,
89
+ "use_cache": true,
90
+ "use_sliding_window": false,
91
+ "vocab_size": 151936
92
+ },
93
+ "tie_word_embeddings": true,
94
+ "timestamp_token_id": 151705,
95
+ "token_classification_bias": false,
96
+ "transformers_version": "5.13.0.dev0",
97
+ "vocab_size": 500
98
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": false,
3
+ "eos_token_id": [
4
+ 151643,
5
+ 151645
6
+ ],
7
+ "max_new_tokens": 512,
8
+ "pad_token_id": 151645,
9
+ "transformers_version": "5.13.0.dev0"
10
+ }
processor_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "chunk_length": 30,
4
+ "dither": 0.0,
5
+ "feature_extractor_type": "Qwen3ASRFeatureExtractor",
6
+ "feature_size": 128,
7
+ "hop_length": 160,
8
+ "min_length": 8000,
9
+ "n_fft": 400,
10
+ "n_samples": 480000,
11
+ "n_window": 50,
12
+ "nb_max_frames": 3000,
13
+ "padding_side": "right",
14
+ "padding_value": 0.0,
15
+ "return_attention_mask": true,
16
+ "sampling_rate": 16000
17
+ },
18
+ "processor_class": "Qwen3ASRProcessor",
19
+ "timestamp_segment_time": 80
20
+ }
tokenizer.json ADDED
@@ -0,0 +1,2109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 500,
8
+ "content": "<|endoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 501,
17
+ "content": "<|im_start|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 502,
26
+ "content": "<|im_end|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 503,
35
+ "content": "<|object_ref_start|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 504,
44
+ "content": "<|object_ref_end|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 505,
53
+ "content": "<|box_start|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 506,
62
+ "content": "<|box_end|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 507,
71
+ "content": "<|quad_start|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 508,
80
+ "content": "<|quad_end|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 509,
89
+ "content": "<|vision_start|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 510,
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 511,
107
+ "content": "<|vision_pad|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 512,
116
+ "content": "<|image_pad|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 513,
125
+ "content": "<|video_pad|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 514,
134
+ "content": "<tool_call>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": false
140
+ },
141
+ {
142
+ "id": 515,
143
+ "content": "</tool_call>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": false
149
+ },
150
+ {
151
+ "id": 516,
152
+ "content": "<|fim_prefix|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": false
158
+ },
159
+ {
160
+ "id": 517,
161
+ "content": "<|fim_middle|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": false
167
+ },
168
+ {
169
+ "id": 518,
170
+ "content": "<|fim_suffix|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ {
178
+ "id": 519,
179
+ "content": "<|fim_pad|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": false
185
+ },
186
+ {
187
+ "id": 520,
188
+ "content": "<|repo_name|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": false
194
+ },
195
+ {
196
+ "id": 521,
197
+ "content": "<|file_sep|>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": false
203
+ },
204
+ {
205
+ "id": 522,
206
+ "content": "<tool_response>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": false
212
+ },
213
+ {
214
+ "id": 523,
215
+ "content": "</tool_response>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": false
221
+ },
222
+ {
223
+ "id": 524,
224
+ "content": "<think>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": false
230
+ },
231
+ {
232
+ "id": 525,
233
+ "content": "</think>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": false
239
+ },
240
+ {
241
+ "id": 526,
242
+ "content": "<|audio_start|>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 527,
251
+ "content": "<|audio_end|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 528,
260
+ "content": "<tts_pad>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 529,
269
+ "content": "<tts_text_bos>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 530,
278
+ "content": "<tts_text_eod>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 531,
287
+ "content": "<tts_text_bos_single>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 532,
296
+ "content": "<non_speech>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": false
302
+ },
303
+ {
304
+ "id": 533,
305
+ "content": "<|audio_pad|>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 534,
314
+ "content": "<blank1>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 535,
323
+ "content": "<blank2>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 536,
332
+ "content": "<blank3>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 537,
341
+ "content": "<blank4>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 538,
350
+ "content": "<blank5>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 539,
359
+ "content": "<blank6>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 540,
368
+ "content": "<blank7>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 541,
377
+ "content": "<blank8>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 542,
386
+ "content": "<blank9>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 543,
395
+ "content": "<blank10>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 544,
404
+ "content": "<blank11>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 545,
413
+ "content": "<blank12>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 546,
422
+ "content": "<blank13>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 547,
431
+ "content": "<blank14>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 548,
440
+ "content": "<blank15>",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ },
447
+ {
448
+ "id": 549,
449
+ "content": "<blank16>",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
+ },
456
+ {
457
+ "id": 550,
458
+ "content": "<blank17>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
+ },
465
+ {
466
+ "id": 551,
467
+ "content": "<blank18>",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
+ },
474
+ {
475
+ "id": 552,
476
+ "content": "<blank19>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
+ },
483
+ {
484
+ "id": 553,
485
+ "content": "<blank20>",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": false,
490
+ "special": true
491
+ },
492
+ {
493
+ "id": 554,
494
+ "content": "<blank21>",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": false,
499
+ "special": true
500
+ },
501
+ {
502
+ "id": 555,
503
+ "content": "<blank22>",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": false,
508
+ "special": true
509
+ },
510
+ {
511
+ "id": 556,
512
+ "content": "<blank23>",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": false,
517
+ "special": true
518
+ },
519
+ {
520
+ "id": 557,
521
+ "content": "<blank24>",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": false,
526
+ "special": true
527
+ },
528
+ {
529
+ "id": 558,
530
+ "content": "<blank25>",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": false,
535
+ "special": true
536
+ },
537
+ {
538
+ "id": 559,
539
+ "content": "<blank26>",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": false,
544
+ "special": true
545
+ },
546
+ {
547
+ "id": 560,
548
+ "content": "<blank27>",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": false,
553
+ "special": true
554
+ },
555
+ {
556
+ "id": 561,
557
+ "content": "<asr_text>",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": false,
562
+ "special": false
563
+ }
564
+ ],
565
+ "normalizer": {
566
+ "type": "NFC"
567
+ },
568
+ "pre_tokenizer": {
569
+ "type": "Sequence",
570
+ "pretokenizers": [
571
+ {
572
+ "type": "Split",
573
+ "pattern": {
574
+ "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
575
+ },
576
+ "behavior": "Isolated",
577
+ "invert": false
578
+ },
579
+ {
580
+ "type": "ByteLevel",
581
+ "add_prefix_space": false,
582
+ "trim_offsets": true,
583
+ "use_regex": false
584
+ }
585
+ ]
586
+ },
587
+ "post_processor": {
588
+ "type": "TemplateProcessing",
589
+ "single": [
590
+ {
591
+ "Sequence": {
592
+ "id": "A",
593
+ "type_id": 0
594
+ }
595
+ }
596
+ ],
597
+ "pair": [
598
+ {
599
+ "Sequence": {
600
+ "id": "A",
601
+ "type_id": 0
602
+ }
603
+ },
604
+ {
605
+ "Sequence": {
606
+ "id": "B",
607
+ "type_id": 1
608
+ }
609
+ }
610
+ ],
611
+ "special_tokens": {}
612
+ },
613
+ "decoder": {
614
+ "type": "ByteLevel",
615
+ "add_prefix_space": true,
616
+ "trim_offsets": true,
617
+ "use_regex": true
618
+ },
619
+ "model": {
620
+ "type": "BPE",
621
+ "dropout": null,
622
+ "unk_token": null,
623
+ "continuing_subword_prefix": "",
624
+ "end_of_word_suffix": "",
625
+ "fuse_unk": false,
626
+ "byte_fallback": false,
627
+ "ignore_merges": false,
628
+ "vocab": {
629
+ "!": 0,
630
+ "\"": 1,
631
+ "#": 2,
632
+ "$": 3,
633
+ "%": 4,
634
+ "&": 5,
635
+ "'": 6,
636
+ "(": 7,
637
+ ")": 8,
638
+ "*": 9,
639
+ "+": 10,
640
+ ",": 11,
641
+ "-": 12,
642
+ ".": 13,
643
+ "/": 14,
644
+ "0": 15,
645
+ "1": 16,
646
+ "2": 17,
647
+ "3": 18,
648
+ "4": 19,
649
+ "5": 20,
650
+ "6": 21,
651
+ "7": 22,
652
+ "8": 23,
653
+ "9": 24,
654
+ ":": 25,
655
+ ";": 26,
656
+ "<": 27,
657
+ "=": 28,
658
+ ">": 29,
659
+ "?": 30,
660
+ "@": 31,
661
+ "A": 32,
662
+ "B": 33,
663
+ "C": 34,
664
+ "D": 35,
665
+ "E": 36,
666
+ "F": 37,
667
+ "G": 38,
668
+ "H": 39,
669
+ "I": 40,
670
+ "J": 41,
671
+ "K": 42,
672
+ "L": 43,
673
+ "M": 44,
674
+ "N": 45,
675
+ "O": 46,
676
+ "P": 47,
677
+ "Q": 48,
678
+ "R": 49,
679
+ "S": 50,
680
+ "T": 51,
681
+ "U": 52,
682
+ "V": 53,
683
+ "W": 54,
684
+ "X": 55,
685
+ "Y": 56,
686
+ "Z": 57,
687
+ "[": 58,
688
+ "\\": 59,
689
+ "]": 60,
690
+ "^": 61,
691
+ "_": 62,
692
+ "`": 63,
693
+ "a": 64,
694
+ "b": 65,
695
+ "c": 66,
696
+ "d": 67,
697
+ "e": 68,
698
+ "f": 69,
699
+ "g": 70,
700
+ "h": 71,
701
+ "i": 72,
702
+ "j": 73,
703
+ "k": 74,
704
+ "l": 75,
705
+ "m": 76,
706
+ "n": 77,
707
+ "o": 78,
708
+ "p": 79,
709
+ "q": 80,
710
+ "r": 81,
711
+ "s": 82,
712
+ "t": 83,
713
+ "u": 84,
714
+ "v": 85,
715
+ "w": 86,
716
+ "x": 87,
717
+ "y": 88,
718
+ "z": 89,
719
+ "{": 90,
720
+ "|": 91,
721
+ "}": 92,
722
+ "~": 93,
723
+ "¡": 94,
724
+ "¢": 95,
725
+ "£": 96,
726
+ "¤": 97,
727
+ "¥": 98,
728
+ "¦": 99,
729
+ "§": 100,
730
+ "¨": 101,
731
+ "©": 102,
732
+ "ª": 103,
733
+ "«": 104,
734
+ "¬": 105,
735
+ "®": 106,
736
+ "¯": 107,
737
+ "°": 108,
738
+ "±": 109,
739
+ "²": 110,
740
+ "³": 111,
741
+ "´": 112,
742
+ "µ": 113,
743
+ "¶": 114,
744
+ "·": 115,
745
+ "¸": 116,
746
+ "¹": 117,
747
+ "º": 118,
748
+ "»": 119,
749
+ "¼": 120,
750
+ "½": 121,
751
+ "¾": 122,
752
+ "¿": 123,
753
+ "À": 124,
754
+ "Á": 125,
755
+ "Â": 126,
756
+ "Ã": 127,
757
+ "Ä": 128,
758
+ "Å": 129,
759
+ "Æ": 130,
760
+ "Ç": 131,
761
+ "È": 132,
762
+ "É": 133,
763
+ "Ê": 134,
764
+ "Ë": 135,
765
+ "Ì": 136,
766
+ "Í": 137,
767
+ "Î": 138,
768
+ "Ï": 139,
769
+ "Ð": 140,
770
+ "Ñ": 141,
771
+ "Ò": 142,
772
+ "Ó": 143,
773
+ "Ô": 144,
774
+ "Õ": 145,
775
+ "Ö": 146,
776
+ "×": 147,
777
+ "Ø": 148,
778
+ "Ù": 149,
779
+ "Ú": 150,
780
+ "Û": 151,
781
+ "Ü": 152,
782
+ "Ý": 153,
783
+ "Þ": 154,
784
+ "ß": 155,
785
+ "à": 156,
786
+ "á": 157,
787
+ "â": 158,
788
+ "ã": 159,
789
+ "ä": 160,
790
+ "å": 161,
791
+ "æ": 162,
792
+ "ç": 163,
793
+ "è": 164,
794
+ "é": 165,
795
+ "ê": 166,
796
+ "ë": 167,
797
+ "ì": 168,
798
+ "í": 169,
799
+ "î": 170,
800
+ "ï": 171,
801
+ "ð": 172,
802
+ "ñ": 173,
803
+ "ò": 174,
804
+ "ó": 175,
805
+ "ô": 176,
806
+ "õ": 177,
807
+ "ö": 178,
808
+ "÷": 179,
809
+ "ø": 180,
810
+ "ù": 181,
811
+ "ú": 182,
812
+ "û": 183,
813
+ "ü": 184,
814
+ "ý": 185,
815
+ "þ": 186,
816
+ "ÿ": 187,
817
+ "Ā": 188,
818
+ "ā": 189,
819
+ "Ă": 190,
820
+ "ă": 191,
821
+ "Ą": 192,
822
+ "ą": 193,
823
+ "Ć": 194,
824
+ "ć": 195,
825
+ "Ĉ": 196,
826
+ "ĉ": 197,
827
+ "Ċ": 198,
828
+ "ċ": 199,
829
+ "Č": 200,
830
+ "č": 201,
831
+ "Ď": 202,
832
+ "ď": 203,
833
+ "Đ": 204,
834
+ "đ": 205,
835
+ "Ē": 206,
836
+ "ē": 207,
837
+ "Ĕ": 208,
838
+ "ĕ": 209,
839
+ "Ė": 210,
840
+ "ė": 211,
841
+ "Ę": 212,
842
+ "ę": 213,
843
+ "Ě": 214,
844
+ "ě": 215,
845
+ "Ĝ": 216,
846
+ "ĝ": 217,
847
+ "Ğ": 218,
848
+ "ğ": 219,
849
+ "Ġ": 220,
850
+ "ġ": 221,
851
+ "Ģ": 222,
852
+ "ģ": 223,
853
+ "Ĥ": 224,
854
+ "ĥ": 225,
855
+ "Ħ": 226,
856
+ "ħ": 227,
857
+ "Ĩ": 228,
858
+ "ĩ": 229,
859
+ "Ī": 230,
860
+ "ī": 231,
861
+ "Ĭ": 232,
862
+ "ĭ": 233,
863
+ "Į": 234,
864
+ "į": 235,
865
+ "İ": 236,
866
+ "ı": 237,
867
+ "IJ": 238,
868
+ "ij": 239,
869
+ "Ĵ": 240,
870
+ "ĵ": 241,
871
+ "Ķ": 242,
872
+ "ķ": 243,
873
+ "ĸ": 244,
874
+ "Ĺ": 245,
875
+ "ĺ": 246,
876
+ "Ļ": 247,
877
+ "ļ": 248,
878
+ "Ľ": 249,
879
+ "ľ": 250,
880
+ "Ŀ": 251,
881
+ "ŀ": 252,
882
+ "Ł": 253,
883
+ "ł": 254,
884
+ "Ń": 255,
885
+ "ĠĠ": 256,
886
+ "ĠĠĠĠ": 257,
887
+ "in": 258,
888
+ "Ġt": 259,
889
+ "ĠĠĠĠĠĠĠĠ": 260,
890
+ "er": 261,
891
+ "ĠĠĠ": 262,
892
+ "on": 263,
893
+ "Ġa": 264,
894
+ "re": 265,
895
+ "at": 266,
896
+ "st": 267,
897
+ "en": 268,
898
+ "or": 269,
899
+ "Ġth": 270,
900
+ "ĊĊ": 271,
901
+ "Ġc": 272,
902
+ "le": 273,
903
+ "Ġs": 274,
904
+ "it": 275,
905
+ "an": 276,
906
+ "ar": 277,
907
+ "al": 278,
908
+ "Ġthe": 279,
909
+ ";Ċ": 280,
910
+ "Ġp": 281,
911
+ "Ġf": 282,
912
+ "ou": 283,
913
+ "Ġ=": 284,
914
+ "is": 285,
915
+ "ĠĠĠĠĠĠĠ": 286,
916
+ "ing": 287,
917
+ "es": 288,
918
+ "Ġw": 289,
919
+ "ion": 290,
920
+ "ed": 291,
921
+ "ic": 292,
922
+ "Ġb": 293,
923
+ "Ġd": 294,
924
+ "et": 295,
925
+ "Ġm": 296,
926
+ "Ġo": 297,
927
+ "ĉĉ": 298,
928
+ "ro": 299,
929
+ "as": 300,
930
+ "el": 301,
931
+ "ct": 302,
932
+ "nd": 303,
933
+ "Ġin": 304,
934
+ "Ġh": 305,
935
+ "ent": 306,
936
+ "id": 307,
937
+ "Ġn": 308,
938
+ "am": 309,
939
+ "ĠĠĠĠĠĠĠĠĠĠĠ": 310,
940
+ "Ġto": 311,
941
+ "Ġre": 312,
942
+ "--": 313,
943
+ "Ġ{": 314,
944
+ "Ġof": 315,
945
+ "om": 316,
946
+ ");Ċ": 317,
947
+ "im": 318,
948
+ "čĊ": 319,
949
+ "Ġ(": 320,
950
+ "il": 321,
951
+ "//": 322,
952
+ "Ġand": 323,
953
+ "ur": 324,
954
+ "se": 325,
955
+ "Ġl": 326,
956
+ "ex": 327,
957
+ "ĠS": 328,
958
+ "ad": 329,
959
+ "Ġ\"": 330,
960
+ "ch": 331,
961
+ "ut": 332,
962
+ "if": 333,
963
+ "**": 334,
964
+ "Ġ}": 335,
965
+ "em": 336,
966
+ "ol": 337,
967
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 338,
968
+ "th": 339,
969
+ ")Ċ": 340,
970
+ "Ġ{Ċ": 341,
971
+ "Ġg": 342,
972
+ "ig": 343,
973
+ "iv": 344,
974
+ ",Ċ": 345,
975
+ "ce": 346,
976
+ "od": 347,
977
+ "Ġv": 348,
978
+ "ate": 349,
979
+ "ĠT": 350,
980
+ "ag": 351,
981
+ "ay": 352,
982
+ "Ġ*": 353,
983
+ "ot": 354,
984
+ "us": 355,
985
+ "ĠC": 356,
986
+ "Ġst": 357,
987
+ "ĠI": 358,
988
+ "un": 359,
989
+ "ul": 360,
990
+ "ue": 361,
991
+ "ĠA": 362,
992
+ "ow": 363,
993
+ "Ġ'": 364,
994
+ "ew": 365,
995
+ "Ġ<": 366,
996
+ "ation": 367,
997
+ "()": 368,
998
+ "Ġfor": 369,
999
+ "ab": 370,
1000
+ "ort": 371,
1001
+ "um": 372,
1002
+ "ame": 373,
1003
+ "Ġis": 374,
1004
+ "pe": 375,
1005
+ "tr": 376,
1006
+ "ck": 377,
1007
+ "âĢ": 378,
1008
+ "Ġy": 379,
1009
+ "ist": 380,
1010
+ "----": 381,
1011
+ ".ĊĊ": 382,
1012
+ "he": 383,
1013
+ "Ġe": 384,
1014
+ "lo": 385,
1015
+ "ĠM": 386,
1016
+ "Ġbe": 387,
1017
+ "ers": 388,
1018
+ "Ġon": 389,
1019
+ "Ġcon": 390,
1020
+ "ap": 391,
1021
+ "ub": 392,
1022
+ "ĠP": 393,
1023
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 394,
1024
+ "ass": 395,
1025
+ "int": 396,
1026
+ ">Ċ": 397,
1027
+ "ly": 398,
1028
+ "urn": 399,
1029
+ "Ġ$": 400,
1030
+ ";ĊĊ": 401,
1031
+ "av": 402,
1032
+ "port": 403,
1033
+ "ir": 404,
1034
+ "->": 405,
1035
+ "nt": 406,
1036
+ "ction": 407,
1037
+ "end": 408,
1038
+ "Ġde": 409,
1039
+ "ith": 410,
1040
+ "out": 411,
1041
+ "turn": 412,
1042
+ "our": 413,
1043
+ "ĠĠĠĠĠ": 414,
1044
+ "lic": 415,
1045
+ "res": 416,
1046
+ "pt": 417,
1047
+ "==": 418,
1048
+ "Ġthis": 419,
1049
+ "Ġwh": 420,
1050
+ "Ġif": 421,
1051
+ "ĠD": 422,
1052
+ "ver": 423,
1053
+ "age": 424,
1054
+ "ĠB": 425,
1055
+ "ht": 426,
1056
+ "ext": 427,
1057
+ "=\"": 428,
1058
+ "Ġthat": 429,
1059
+ "****": 430,
1060
+ "ĠR": 431,
1061
+ "Ġit": 432,
1062
+ "ess": 433,
1063
+ "ĠF": 434,
1064
+ "Ġr": 435,
1065
+ "os": 436,
1066
+ "and": 437,
1067
+ "Ġas": 438,
1068
+ "ect": 439,
1069
+ "ke": 440,
1070
+ "rom": 441,
1071
+ "Ġ//": 442,
1072
+ "con": 443,
1073
+ "ĠL": 444,
1074
+ "(\"": 445,
1075
+ "qu": 446,
1076
+ "lass": 447,
1077
+ "Ġwith": 448,
1078
+ "iz": 449,
1079
+ "de": 450,
1080
+ "ĠN": 451,
1081
+ "Ġal": 452,
1082
+ "op": 453,
1083
+ "up": 454,
1084
+ "get": 455,
1085
+ "Ġ}Ċ": 456,
1086
+ "ile": 457,
1087
+ "Ġan": 458,
1088
+ "ata": 459,
1089
+ "ore": 460,
1090
+ "ri": 461,
1091
+ "Ġpro": 462,
1092
+ ";čĊ": 463,
1093
+ "ĉĉĉĉ": 464,
1094
+ "ter": 465,
1095
+ "ain": 466,
1096
+ "ĠW": 467,
1097
+ "ĠE": 468,
1098
+ "Ġcom": 469,
1099
+ "Ġreturn": 470,
1100
+ "art": 471,
1101
+ "ĠH": 472,
1102
+ "ack": 473,
1103
+ "import": 474,
1104
+ "ublic": 475,
1105
+ "Ġor": 476,
1106
+ "est": 477,
1107
+ "ment": 478,
1108
+ "ĠG": 479,
1109
+ "able": 480,
1110
+ "Ġ-": 481,
1111
+ "ine": 482,
1112
+ "ill": 483,
1113
+ "ind": 484,
1114
+ "ere": 485,
1115
+ "::": 486,
1116
+ "ity": 487,
1117
+ "Ġ+": 488,
1118
+ "Ġtr": 489,
1119
+ "elf": 490,
1120
+ "ight": 491,
1121
+ "('": 492,
1122
+ "orm": 493,
1123
+ "ult": 494,
1124
+ "str": 495,
1125
+ "..": 496,
1126
+ "\",": 497,
1127
+ "Ġyou": 498,
1128
+ "ype": 499
1129
+ },
1130
+ "merges": [
1131
+ [
1132
+ "Ġ",
1133
+ "Ġ"
1134
+ ],
1135
+ [
1136
+ "ĠĠ",
1137
+ "ĠĠ"
1138
+ ],
1139
+ [
1140
+ "i",
1141
+ "n"
1142
+ ],
1143
+ [
1144
+ "Ġ",
1145
+ "t"
1146
+ ],
1147
+ [
1148
+ "ĠĠĠĠ",
1149
+ "ĠĠĠĠ"
1150
+ ],
1151
+ [
1152
+ "e",
1153
+ "r"
1154
+ ],
1155
+ [
1156
+ "ĠĠ",
1157
+ "Ġ"
1158
+ ],
1159
+ [
1160
+ "o",
1161
+ "n"
1162
+ ],
1163
+ [
1164
+ "Ġ",
1165
+ "a"
1166
+ ],
1167
+ [
1168
+ "r",
1169
+ "e"
1170
+ ],
1171
+ [
1172
+ "a",
1173
+ "t"
1174
+ ],
1175
+ [
1176
+ "s",
1177
+ "t"
1178
+ ],
1179
+ [
1180
+ "e",
1181
+ "n"
1182
+ ],
1183
+ [
1184
+ "o",
1185
+ "r"
1186
+ ],
1187
+ [
1188
+ "Ġt",
1189
+ "h"
1190
+ ],
1191
+ [
1192
+ "Ċ",
1193
+ "Ċ"
1194
+ ],
1195
+ [
1196
+ "Ġ",
1197
+ "c"
1198
+ ],
1199
+ [
1200
+ "l",
1201
+ "e"
1202
+ ],
1203
+ [
1204
+ "Ġ",
1205
+ "s"
1206
+ ],
1207
+ [
1208
+ "i",
1209
+ "t"
1210
+ ],
1211
+ [
1212
+ "a",
1213
+ "n"
1214
+ ],
1215
+ [
1216
+ "a",
1217
+ "r"
1218
+ ],
1219
+ [
1220
+ "a",
1221
+ "l"
1222
+ ],
1223
+ [
1224
+ "Ġth",
1225
+ "e"
1226
+ ],
1227
+ [
1228
+ ";",
1229
+ "Ċ"
1230
+ ],
1231
+ [
1232
+ "Ġ",
1233
+ "p"
1234
+ ],
1235
+ [
1236
+ "Ġ",
1237
+ "f"
1238
+ ],
1239
+ [
1240
+ "o",
1241
+ "u"
1242
+ ],
1243
+ [
1244
+ "Ġ",
1245
+ "="
1246
+ ],
1247
+ [
1248
+ "i",
1249
+ "s"
1250
+ ],
1251
+ [
1252
+ "ĠĠĠĠ",
1253
+ "ĠĠĠ"
1254
+ ],
1255
+ [
1256
+ "in",
1257
+ "g"
1258
+ ],
1259
+ [
1260
+ "e",
1261
+ "s"
1262
+ ],
1263
+ [
1264
+ "Ġ",
1265
+ "w"
1266
+ ],
1267
+ [
1268
+ "i",
1269
+ "on"
1270
+ ],
1271
+ [
1272
+ "e",
1273
+ "d"
1274
+ ],
1275
+ [
1276
+ "i",
1277
+ "c"
1278
+ ],
1279
+ [
1280
+ "Ġ",
1281
+ "b"
1282
+ ],
1283
+ [
1284
+ "Ġ",
1285
+ "d"
1286
+ ],
1287
+ [
1288
+ "e",
1289
+ "t"
1290
+ ],
1291
+ [
1292
+ "Ġ",
1293
+ "m"
1294
+ ],
1295
+ [
1296
+ "Ġ",
1297
+ "o"
1298
+ ],
1299
+ [
1300
+ "ĉ",
1301
+ "ĉ"
1302
+ ],
1303
+ [
1304
+ "r",
1305
+ "o"
1306
+ ],
1307
+ [
1308
+ "a",
1309
+ "s"
1310
+ ],
1311
+ [
1312
+ "e",
1313
+ "l"
1314
+ ],
1315
+ [
1316
+ "c",
1317
+ "t"
1318
+ ],
1319
+ [
1320
+ "n",
1321
+ "d"
1322
+ ],
1323
+ [
1324
+ "Ġ",
1325
+ "in"
1326
+ ],
1327
+ [
1328
+ "Ġ",
1329
+ "h"
1330
+ ],
1331
+ [
1332
+ "en",
1333
+ "t"
1334
+ ],
1335
+ [
1336
+ "i",
1337
+ "d"
1338
+ ],
1339
+ [
1340
+ "Ġ",
1341
+ "n"
1342
+ ],
1343
+ [
1344
+ "a",
1345
+ "m"
1346
+ ],
1347
+ [
1348
+ "ĠĠĠĠĠĠĠĠ",
1349
+ "ĠĠĠ"
1350
+ ],
1351
+ [
1352
+ "Ġt",
1353
+ "o"
1354
+ ],
1355
+ [
1356
+ "Ġ",
1357
+ "re"
1358
+ ],
1359
+ [
1360
+ "-",
1361
+ "-"
1362
+ ],
1363
+ [
1364
+ "Ġ",
1365
+ "{"
1366
+ ],
1367
+ [
1368
+ "Ġo",
1369
+ "f"
1370
+ ],
1371
+ [
1372
+ "o",
1373
+ "m"
1374
+ ],
1375
+ [
1376
+ ")",
1377
+ ";Ċ"
1378
+ ],
1379
+ [
1380
+ "i",
1381
+ "m"
1382
+ ],
1383
+ [
1384
+ "č",
1385
+ "Ċ"
1386
+ ],
1387
+ [
1388
+ "Ġ",
1389
+ "("
1390
+ ],
1391
+ [
1392
+ "i",
1393
+ "l"
1394
+ ],
1395
+ [
1396
+ "/",
1397
+ "/"
1398
+ ],
1399
+ [
1400
+ "Ġa",
1401
+ "nd"
1402
+ ],
1403
+ [
1404
+ "u",
1405
+ "r"
1406
+ ],
1407
+ [
1408
+ "s",
1409
+ "e"
1410
+ ],
1411
+ [
1412
+ "Ġ",
1413
+ "l"
1414
+ ],
1415
+ [
1416
+ "e",
1417
+ "x"
1418
+ ],
1419
+ [
1420
+ "Ġ",
1421
+ "S"
1422
+ ],
1423
+ [
1424
+ "a",
1425
+ "d"
1426
+ ],
1427
+ [
1428
+ "Ġ",
1429
+ "\""
1430
+ ],
1431
+ [
1432
+ "c",
1433
+ "h"
1434
+ ],
1435
+ [
1436
+ "u",
1437
+ "t"
1438
+ ],
1439
+ [
1440
+ "i",
1441
+ "f"
1442
+ ],
1443
+ [
1444
+ "*",
1445
+ "*"
1446
+ ],
1447
+ [
1448
+ "Ġ",
1449
+ "}"
1450
+ ],
1451
+ [
1452
+ "e",
1453
+ "m"
1454
+ ],
1455
+ [
1456
+ "o",
1457
+ "l"
1458
+ ],
1459
+ [
1460
+ "ĠĠĠĠĠĠĠĠ",
1461
+ "ĠĠĠĠĠĠĠĠ"
1462
+ ],
1463
+ [
1464
+ "t",
1465
+ "h"
1466
+ ],
1467
+ [
1468
+ ")",
1469
+ "Ċ"
1470
+ ],
1471
+ [
1472
+ "Ġ{",
1473
+ "Ċ"
1474
+ ],
1475
+ [
1476
+ "Ġ",
1477
+ "g"
1478
+ ],
1479
+ [
1480
+ "i",
1481
+ "g"
1482
+ ],
1483
+ [
1484
+ "i",
1485
+ "v"
1486
+ ],
1487
+ [
1488
+ ",",
1489
+ "Ċ"
1490
+ ],
1491
+ [
1492
+ "c",
1493
+ "e"
1494
+ ],
1495
+ [
1496
+ "o",
1497
+ "d"
1498
+ ],
1499
+ [
1500
+ "Ġ",
1501
+ "v"
1502
+ ],
1503
+ [
1504
+ "at",
1505
+ "e"
1506
+ ],
1507
+ [
1508
+ "Ġ",
1509
+ "T"
1510
+ ],
1511
+ [
1512
+ "a",
1513
+ "g"
1514
+ ],
1515
+ [
1516
+ "a",
1517
+ "y"
1518
+ ],
1519
+ [
1520
+ "Ġ",
1521
+ "*"
1522
+ ],
1523
+ [
1524
+ "o",
1525
+ "t"
1526
+ ],
1527
+ [
1528
+ "u",
1529
+ "s"
1530
+ ],
1531
+ [
1532
+ "Ġ",
1533
+ "C"
1534
+ ],
1535
+ [
1536
+ "Ġ",
1537
+ "st"
1538
+ ],
1539
+ [
1540
+ "Ġ",
1541
+ "I"
1542
+ ],
1543
+ [
1544
+ "u",
1545
+ "n"
1546
+ ],
1547
+ [
1548
+ "u",
1549
+ "l"
1550
+ ],
1551
+ [
1552
+ "u",
1553
+ "e"
1554
+ ],
1555
+ [
1556
+ "Ġ",
1557
+ "A"
1558
+ ],
1559
+ [
1560
+ "o",
1561
+ "w"
1562
+ ],
1563
+ [
1564
+ "Ġ",
1565
+ "'"
1566
+ ],
1567
+ [
1568
+ "e",
1569
+ "w"
1570
+ ],
1571
+ [
1572
+ "Ġ",
1573
+ "<"
1574
+ ],
1575
+ [
1576
+ "at",
1577
+ "ion"
1578
+ ],
1579
+ [
1580
+ "(",
1581
+ ")"
1582
+ ],
1583
+ [
1584
+ "Ġf",
1585
+ "or"
1586
+ ],
1587
+ [
1588
+ "a",
1589
+ "b"
1590
+ ],
1591
+ [
1592
+ "or",
1593
+ "t"
1594
+ ],
1595
+ [
1596
+ "u",
1597
+ "m"
1598
+ ],
1599
+ [
1600
+ "am",
1601
+ "e"
1602
+ ],
1603
+ [
1604
+ "Ġ",
1605
+ "is"
1606
+ ],
1607
+ [
1608
+ "p",
1609
+ "e"
1610
+ ],
1611
+ [
1612
+ "t",
1613
+ "r"
1614
+ ],
1615
+ [
1616
+ "c",
1617
+ "k"
1618
+ ],
1619
+ [
1620
+ "â",
1621
+ "Ģ"
1622
+ ],
1623
+ [
1624
+ "Ġ",
1625
+ "y"
1626
+ ],
1627
+ [
1628
+ "i",
1629
+ "st"
1630
+ ],
1631
+ [
1632
+ "--",
1633
+ "--"
1634
+ ],
1635
+ [
1636
+ ".",
1637
+ "ĊĊ"
1638
+ ],
1639
+ [
1640
+ "h",
1641
+ "e"
1642
+ ],
1643
+ [
1644
+ "Ġ",
1645
+ "e"
1646
+ ],
1647
+ [
1648
+ "l",
1649
+ "o"
1650
+ ],
1651
+ [
1652
+ "Ġ",
1653
+ "M"
1654
+ ],
1655
+ [
1656
+ "Ġb",
1657
+ "e"
1658
+ ],
1659
+ [
1660
+ "er",
1661
+ "s"
1662
+ ],
1663
+ [
1664
+ "Ġ",
1665
+ "on"
1666
+ ],
1667
+ [
1668
+ "Ġc",
1669
+ "on"
1670
+ ],
1671
+ [
1672
+ "a",
1673
+ "p"
1674
+ ],
1675
+ [
1676
+ "u",
1677
+ "b"
1678
+ ],
1679
+ [
1680
+ "Ġ",
1681
+ "P"
1682
+ ],
1683
+ [
1684
+ "ĠĠĠĠĠĠĠĠ",
1685
+ "ĠĠĠĠĠĠĠ"
1686
+ ],
1687
+ [
1688
+ "as",
1689
+ "s"
1690
+ ],
1691
+ [
1692
+ "in",
1693
+ "t"
1694
+ ],
1695
+ [
1696
+ ">",
1697
+ "Ċ"
1698
+ ],
1699
+ [
1700
+ "l",
1701
+ "y"
1702
+ ],
1703
+ [
1704
+ "ur",
1705
+ "n"
1706
+ ],
1707
+ [
1708
+ "Ġ",
1709
+ "$"
1710
+ ],
1711
+ [
1712
+ ";",
1713
+ "ĊĊ"
1714
+ ],
1715
+ [
1716
+ "a",
1717
+ "v"
1718
+ ],
1719
+ [
1720
+ "p",
1721
+ "ort"
1722
+ ],
1723
+ [
1724
+ "i",
1725
+ "r"
1726
+ ],
1727
+ [
1728
+ "-",
1729
+ ">"
1730
+ ],
1731
+ [
1732
+ "n",
1733
+ "t"
1734
+ ],
1735
+ [
1736
+ "ct",
1737
+ "ion"
1738
+ ],
1739
+ [
1740
+ "en",
1741
+ "d"
1742
+ ],
1743
+ [
1744
+ "Ġd",
1745
+ "e"
1746
+ ],
1747
+ [
1748
+ "it",
1749
+ "h"
1750
+ ],
1751
+ [
1752
+ "ou",
1753
+ "t"
1754
+ ],
1755
+ [
1756
+ "t",
1757
+ "urn"
1758
+ ],
1759
+ [
1760
+ "ou",
1761
+ "r"
1762
+ ],
1763
+ [
1764
+ "ĠĠĠĠ",
1765
+ "Ġ"
1766
+ ],
1767
+ [
1768
+ "l",
1769
+ "ic"
1770
+ ],
1771
+ [
1772
+ "re",
1773
+ "s"
1774
+ ],
1775
+ [
1776
+ "p",
1777
+ "t"
1778
+ ],
1779
+ [
1780
+ "=",
1781
+ "="
1782
+ ],
1783
+ [
1784
+ "Ġth",
1785
+ "is"
1786
+ ],
1787
+ [
1788
+ "Ġw",
1789
+ "h"
1790
+ ],
1791
+ [
1792
+ "Ġ",
1793
+ "if"
1794
+ ],
1795
+ [
1796
+ "Ġ",
1797
+ "D"
1798
+ ],
1799
+ [
1800
+ "v",
1801
+ "er"
1802
+ ],
1803
+ [
1804
+ "ag",
1805
+ "e"
1806
+ ],
1807
+ [
1808
+ "Ġ",
1809
+ "B"
1810
+ ],
1811
+ [
1812
+ "h",
1813
+ "t"
1814
+ ],
1815
+ [
1816
+ "ex",
1817
+ "t"
1818
+ ],
1819
+ [
1820
+ "=",
1821
+ "\""
1822
+ ],
1823
+ [
1824
+ "Ġth",
1825
+ "at"
1826
+ ],
1827
+ [
1828
+ "**",
1829
+ "**"
1830
+ ],
1831
+ [
1832
+ "Ġ",
1833
+ "R"
1834
+ ],
1835
+ [
1836
+ "Ġ",
1837
+ "it"
1838
+ ],
1839
+ [
1840
+ "es",
1841
+ "s"
1842
+ ],
1843
+ [
1844
+ "Ġ",
1845
+ "F"
1846
+ ],
1847
+ [
1848
+ "Ġ",
1849
+ "r"
1850
+ ],
1851
+ [
1852
+ "o",
1853
+ "s"
1854
+ ],
1855
+ [
1856
+ "an",
1857
+ "d"
1858
+ ],
1859
+ [
1860
+ "Ġa",
1861
+ "s"
1862
+ ],
1863
+ [
1864
+ "e",
1865
+ "ct"
1866
+ ],
1867
+ [
1868
+ "k",
1869
+ "e"
1870
+ ],
1871
+ [
1872
+ "ro",
1873
+ "m"
1874
+ ],
1875
+ [
1876
+ "Ġ",
1877
+ "//"
1878
+ ],
1879
+ [
1880
+ "c",
1881
+ "on"
1882
+ ],
1883
+ [
1884
+ "Ġ",
1885
+ "L"
1886
+ ],
1887
+ [
1888
+ "(",
1889
+ "\""
1890
+ ],
1891
+ [
1892
+ "q",
1893
+ "u"
1894
+ ],
1895
+ [
1896
+ "l",
1897
+ "ass"
1898
+ ],
1899
+ [
1900
+ "Ġw",
1901
+ "ith"
1902
+ ],
1903
+ [
1904
+ "i",
1905
+ "z"
1906
+ ],
1907
+ [
1908
+ "d",
1909
+ "e"
1910
+ ],
1911
+ [
1912
+ "Ġ",
1913
+ "N"
1914
+ ],
1915
+ [
1916
+ "Ġa",
1917
+ "l"
1918
+ ],
1919
+ [
1920
+ "o",
1921
+ "p"
1922
+ ],
1923
+ [
1924
+ "u",
1925
+ "p"
1926
+ ],
1927
+ [
1928
+ "g",
1929
+ "et"
1930
+ ],
1931
+ [
1932
+ "Ġ}",
1933
+ "Ċ"
1934
+ ],
1935
+ [
1936
+ "i",
1937
+ "le"
1938
+ ],
1939
+ [
1940
+ "Ġa",
1941
+ "n"
1942
+ ],
1943
+ [
1944
+ "at",
1945
+ "a"
1946
+ ],
1947
+ [
1948
+ "o",
1949
+ "re"
1950
+ ],
1951
+ [
1952
+ "r",
1953
+ "i"
1954
+ ],
1955
+ [
1956
+ "Ġp",
1957
+ "ro"
1958
+ ],
1959
+ [
1960
+ ";",
1961
+ "čĊ"
1962
+ ],
1963
+ [
1964
+ "ĉĉ",
1965
+ "ĉĉ"
1966
+ ],
1967
+ [
1968
+ "t",
1969
+ "er"
1970
+ ],
1971
+ [
1972
+ "a",
1973
+ "in"
1974
+ ],
1975
+ [
1976
+ "Ġ",
1977
+ "W"
1978
+ ],
1979
+ [
1980
+ "Ġ",
1981
+ "E"
1982
+ ],
1983
+ [
1984
+ "Ġc",
1985
+ "om"
1986
+ ],
1987
+ [
1988
+ "Ġre",
1989
+ "turn"
1990
+ ],
1991
+ [
1992
+ "ar",
1993
+ "t"
1994
+ ],
1995
+ [
1996
+ "Ġ",
1997
+ "H"
1998
+ ],
1999
+ [
2000
+ "a",
2001
+ "ck"
2002
+ ],
2003
+ [
2004
+ "im",
2005
+ "port"
2006
+ ],
2007
+ [
2008
+ "ub",
2009
+ "lic"
2010
+ ],
2011
+ [
2012
+ "Ġ",
2013
+ "or"
2014
+ ],
2015
+ [
2016
+ "e",
2017
+ "st"
2018
+ ],
2019
+ [
2020
+ "m",
2021
+ "ent"
2022
+ ],
2023
+ [
2024
+ "Ġ",
2025
+ "G"
2026
+ ],
2027
+ [
2028
+ "ab",
2029
+ "le"
2030
+ ],
2031
+ [
2032
+ "Ġ",
2033
+ "-"
2034
+ ],
2035
+ [
2036
+ "in",
2037
+ "e"
2038
+ ],
2039
+ [
2040
+ "il",
2041
+ "l"
2042
+ ],
2043
+ [
2044
+ "in",
2045
+ "d"
2046
+ ],
2047
+ [
2048
+ "er",
2049
+ "e"
2050
+ ],
2051
+ [
2052
+ ":",
2053
+ ":"
2054
+ ],
2055
+ [
2056
+ "it",
2057
+ "y"
2058
+ ],
2059
+ [
2060
+ "Ġ",
2061
+ "+"
2062
+ ],
2063
+ [
2064
+ "Ġt",
2065
+ "r"
2066
+ ],
2067
+ [
2068
+ "el",
2069
+ "f"
2070
+ ],
2071
+ [
2072
+ "ig",
2073
+ "ht"
2074
+ ],
2075
+ [
2076
+ "(",
2077
+ "'"
2078
+ ],
2079
+ [
2080
+ "or",
2081
+ "m"
2082
+ ],
2083
+ [
2084
+ "ul",
2085
+ "t"
2086
+ ],
2087
+ [
2088
+ "st",
2089
+ "r"
2090
+ ],
2091
+ [
2092
+ ".",
2093
+ "."
2094
+ ],
2095
+ [
2096
+ "\"",
2097
+ ","
2098
+ ],
2099
+ [
2100
+ "Ġy",
2101
+ "ou"
2102
+ ],
2103
+ [
2104
+ "y",
2105
+ "pe"
2106
+ ]
2107
+ ]
2108
+ }
2109
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,530 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "local_files_only": false,
14
+ "model_max_length": 131072,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|endoftext|>",
25
+ "processor_class": "Qwen3ASRProcessor",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "Qwen2Tokenizer",
28
+ "unk_token": null,
29
+ "video_token": "<|video_pad|>",
30
+ "vision_bos_token": "<|vision_start|>",
31
+ "vision_eos_token": "<|vision_end|>",
32
+ "added_tokens_decoder": {
33
+ "500": {
34
+ "content": "<|endoftext|>",
35
+ "single_word": false,
36
+ "lstrip": false,
37
+ "rstrip": false,
38
+ "normalized": false,
39
+ "special": true
40
+ },
41
+ "501": {
42
+ "content": "<|im_start|>",
43
+ "single_word": false,
44
+ "lstrip": false,
45
+ "rstrip": false,
46
+ "normalized": false,
47
+ "special": true
48
+ },
49
+ "502": {
50
+ "content": "<|im_end|>",
51
+ "single_word": false,
52
+ "lstrip": false,
53
+ "rstrip": false,
54
+ "normalized": false,
55
+ "special": true
56
+ },
57
+ "503": {
58
+ "content": "<|object_ref_start|>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ "504": {
66
+ "content": "<|object_ref_end|>",
67
+ "single_word": false,
68
+ "lstrip": false,
69
+ "rstrip": false,
70
+ "normalized": false,
71
+ "special": true
72
+ },
73
+ "505": {
74
+ "content": "<|box_start|>",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": false,
79
+ "special": true
80
+ },
81
+ "506": {
82
+ "content": "<|box_end|>",
83
+ "single_word": false,
84
+ "lstrip": false,
85
+ "rstrip": false,
86
+ "normalized": false,
87
+ "special": true
88
+ },
89
+ "507": {
90
+ "content": "<|quad_start|>",
91
+ "single_word": false,
92
+ "lstrip": false,
93
+ "rstrip": false,
94
+ "normalized": false,
95
+ "special": true
96
+ },
97
+ "508": {
98
+ "content": "<|quad_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ "509": {
106
+ "content": "<|vision_start|>",
107
+ "single_word": false,
108
+ "lstrip": false,
109
+ "rstrip": false,
110
+ "normalized": false,
111
+ "special": true
112
+ },
113
+ "510": {
114
+ "content": "<|vision_end|>",
115
+ "single_word": false,
116
+ "lstrip": false,
117
+ "rstrip": false,
118
+ "normalized": false,
119
+ "special": true
120
+ },
121
+ "511": {
122
+ "content": "<|vision_pad|>",
123
+ "single_word": false,
124
+ "lstrip": false,
125
+ "rstrip": false,
126
+ "normalized": false,
127
+ "special": true
128
+ },
129
+ "512": {
130
+ "content": "<|image_pad|>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": true
136
+ },
137
+ "513": {
138
+ "content": "<|video_pad|>",
139
+ "single_word": false,
140
+ "lstrip": false,
141
+ "rstrip": false,
142
+ "normalized": false,
143
+ "special": true
144
+ },
145
+ "514": {
146
+ "content": "<tool_call>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": false
152
+ },
153
+ "515": {
154
+ "content": "</tool_call>",
155
+ "single_word": false,
156
+ "lstrip": false,
157
+ "rstrip": false,
158
+ "normalized": false,
159
+ "special": false
160
+ },
161
+ "516": {
162
+ "content": "<|fim_prefix|>",
163
+ "single_word": false,
164
+ "lstrip": false,
165
+ "rstrip": false,
166
+ "normalized": false,
167
+ "special": false
168
+ },
169
+ "517": {
170
+ "content": "<|fim_middle|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ "518": {
178
+ "content": "<|fim_suffix|>",
179
+ "single_word": false,
180
+ "lstrip": false,
181
+ "rstrip": false,
182
+ "normalized": false,
183
+ "special": false
184
+ },
185
+ "519": {
186
+ "content": "<|fim_pad|>",
187
+ "single_word": false,
188
+ "lstrip": false,
189
+ "rstrip": false,
190
+ "normalized": false,
191
+ "special": false
192
+ },
193
+ "520": {
194
+ "content": "<|repo_name|>",
195
+ "single_word": false,
196
+ "lstrip": false,
197
+ "rstrip": false,
198
+ "normalized": false,
199
+ "special": false
200
+ },
201
+ "521": {
202
+ "content": "<|file_sep|>",
203
+ "single_word": false,
204
+ "lstrip": false,
205
+ "rstrip": false,
206
+ "normalized": false,
207
+ "special": false
208
+ },
209
+ "522": {
210
+ "content": "<tool_response>",
211
+ "single_word": false,
212
+ "lstrip": false,
213
+ "rstrip": false,
214
+ "normalized": false,
215
+ "special": false
216
+ },
217
+ "523": {
218
+ "content": "</tool_response>",
219
+ "single_word": false,
220
+ "lstrip": false,
221
+ "rstrip": false,
222
+ "normalized": false,
223
+ "special": false
224
+ },
225
+ "524": {
226
+ "content": "<think>",
227
+ "single_word": false,
228
+ "lstrip": false,
229
+ "rstrip": false,
230
+ "normalized": false,
231
+ "special": false
232
+ },
233
+ "525": {
234
+ "content": "</think>",
235
+ "single_word": false,
236
+ "lstrip": false,
237
+ "rstrip": false,
238
+ "normalized": false,
239
+ "special": false
240
+ },
241
+ "526": {
242
+ "content": "<|audio_start|>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ "527": {
250
+ "content": "<|audio_end|>",
251
+ "single_word": false,
252
+ "lstrip": false,
253
+ "rstrip": false,
254
+ "normalized": false,
255
+ "special": true
256
+ },
257
+ "528": {
258
+ "content": "<tts_pad>",
259
+ "single_word": false,
260
+ "lstrip": false,
261
+ "rstrip": false,
262
+ "normalized": false,
263
+ "special": true
264
+ },
265
+ "529": {
266
+ "content": "<tts_text_bos>",
267
+ "single_word": false,
268
+ "lstrip": false,
269
+ "rstrip": false,
270
+ "normalized": false,
271
+ "special": true
272
+ },
273
+ "530": {
274
+ "content": "<tts_text_eod>",
275
+ "single_word": false,
276
+ "lstrip": false,
277
+ "rstrip": false,
278
+ "normalized": false,
279
+ "special": true
280
+ },
281
+ "531": {
282
+ "content": "<tts_text_bos_single>",
283
+ "single_word": false,
284
+ "lstrip": false,
285
+ "rstrip": false,
286
+ "normalized": false,
287
+ "special": true
288
+ },
289
+ "532": {
290
+ "content": "<non_speech>",
291
+ "single_word": false,
292
+ "lstrip": false,
293
+ "rstrip": false,
294
+ "normalized": false,
295
+ "special": false
296
+ },
297
+ "533": {
298
+ "content": "<|audio_pad|>",
299
+ "single_word": false,
300
+ "lstrip": false,
301
+ "rstrip": false,
302
+ "normalized": false,
303
+ "special": true
304
+ },
305
+ "534": {
306
+ "content": "<blank1>",
307
+ "single_word": false,
308
+ "lstrip": false,
309
+ "rstrip": false,
310
+ "normalized": false,
311
+ "special": true
312
+ },
313
+ "535": {
314
+ "content": "<blank2>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ "536": {
322
+ "content": "<blank3>",
323
+ "single_word": false,
324
+ "lstrip": false,
325
+ "rstrip": false,
326
+ "normalized": false,
327
+ "special": true
328
+ },
329
+ "537": {
330
+ "content": "<blank4>",
331
+ "single_word": false,
332
+ "lstrip": false,
333
+ "rstrip": false,
334
+ "normalized": false,
335
+ "special": true
336
+ },
337
+ "538": {
338
+ "content": "<blank5>",
339
+ "single_word": false,
340
+ "lstrip": false,
341
+ "rstrip": false,
342
+ "normalized": false,
343
+ "special": true
344
+ },
345
+ "539": {
346
+ "content": "<blank6>",
347
+ "single_word": false,
348
+ "lstrip": false,
349
+ "rstrip": false,
350
+ "normalized": false,
351
+ "special": true
352
+ },
353
+ "540": {
354
+ "content": "<blank7>",
355
+ "single_word": false,
356
+ "lstrip": false,
357
+ "rstrip": false,
358
+ "normalized": false,
359
+ "special": true
360
+ },
361
+ "541": {
362
+ "content": "<blank8>",
363
+ "single_word": false,
364
+ "lstrip": false,
365
+ "rstrip": false,
366
+ "normalized": false,
367
+ "special": true
368
+ },
369
+ "542": {
370
+ "content": "<blank9>",
371
+ "single_word": false,
372
+ "lstrip": false,
373
+ "rstrip": false,
374
+ "normalized": false,
375
+ "special": true
376
+ },
377
+ "543": {
378
+ "content": "<blank10>",
379
+ "single_word": false,
380
+ "lstrip": false,
381
+ "rstrip": false,
382
+ "normalized": false,
383
+ "special": true
384
+ },
385
+ "544": {
386
+ "content": "<blank11>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ "545": {
394
+ "content": "<blank12>",
395
+ "single_word": false,
396
+ "lstrip": false,
397
+ "rstrip": false,
398
+ "normalized": false,
399
+ "special": true
400
+ },
401
+ "546": {
402
+ "content": "<blank13>",
403
+ "single_word": false,
404
+ "lstrip": false,
405
+ "rstrip": false,
406
+ "normalized": false,
407
+ "special": true
408
+ },
409
+ "547": {
410
+ "content": "<blank14>",
411
+ "single_word": false,
412
+ "lstrip": false,
413
+ "rstrip": false,
414
+ "normalized": false,
415
+ "special": true
416
+ },
417
+ "548": {
418
+ "content": "<blank15>",
419
+ "single_word": false,
420
+ "lstrip": false,
421
+ "rstrip": false,
422
+ "normalized": false,
423
+ "special": true
424
+ },
425
+ "549": {
426
+ "content": "<blank16>",
427
+ "single_word": false,
428
+ "lstrip": false,
429
+ "rstrip": false,
430
+ "normalized": false,
431
+ "special": true
432
+ },
433
+ "550": {
434
+ "content": "<blank17>",
435
+ "single_word": false,
436
+ "lstrip": false,
437
+ "rstrip": false,
438
+ "normalized": false,
439
+ "special": true
440
+ },
441
+ "551": {
442
+ "content": "<blank18>",
443
+ "single_word": false,
444
+ "lstrip": false,
445
+ "rstrip": false,
446
+ "normalized": false,
447
+ "special": true
448
+ },
449
+ "552": {
450
+ "content": "<blank19>",
451
+ "single_word": false,
452
+ "lstrip": false,
453
+ "rstrip": false,
454
+ "normalized": false,
455
+ "special": true
456
+ },
457
+ "553": {
458
+ "content": "<blank20>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
+ },
465
+ "554": {
466
+ "content": "<blank21>",
467
+ "single_word": false,
468
+ "lstrip": false,
469
+ "rstrip": false,
470
+ "normalized": false,
471
+ "special": true
472
+ },
473
+ "555": {
474
+ "content": "<blank22>",
475
+ "single_word": false,
476
+ "lstrip": false,
477
+ "rstrip": false,
478
+ "normalized": false,
479
+ "special": true
480
+ },
481
+ "556": {
482
+ "content": "<blank23>",
483
+ "single_word": false,
484
+ "lstrip": false,
485
+ "rstrip": false,
486
+ "normalized": false,
487
+ "special": true
488
+ },
489
+ "557": {
490
+ "content": "<blank24>",
491
+ "single_word": false,
492
+ "lstrip": false,
493
+ "rstrip": false,
494
+ "normalized": false,
495
+ "special": true
496
+ },
497
+ "558": {
498
+ "content": "<blank25>",
499
+ "single_word": false,
500
+ "lstrip": false,
501
+ "rstrip": false,
502
+ "normalized": false,
503
+ "special": true
504
+ },
505
+ "559": {
506
+ "content": "<blank26>",
507
+ "single_word": false,
508
+ "lstrip": false,
509
+ "rstrip": false,
510
+ "normalized": false,
511
+ "special": true
512
+ },
513
+ "560": {
514
+ "content": "<blank27>",
515
+ "single_word": false,
516
+ "lstrip": false,
517
+ "rstrip": false,
518
+ "normalized": false,
519
+ "special": true
520
+ },
521
+ "561": {
522
+ "content": "<asr_text>",
523
+ "single_word": false,
524
+ "lstrip": false,
525
+ "rstrip": false,
526
+ "normalized": false,
527
+ "special": false
528
+ }
529
+ }
530
+ }