hf-transformers-bot commited on
Commit
9df5cd1
·
verified ·
1 Parent(s): 7945365

Add tiny processor fixture for testing

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
37
+ figures/language_distribution_horizontal.png filter=lfs diff=lfs merge=lfs -text
38
+ figures/VibeVoice_ASR_archi.png filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set system_prompt = system_prompt | default("You are a helpful assistant that transcribes audio input into text output in JSON format.") -%}
2
+ <|im_start|>system
3
+ {{ system_prompt }}<|im_end|>
4
+ {%- set audio_token = audio_token | default("<|box_start|>") -%}
5
+ {%- set audio_start_token = "<|object_ref_start|>" -%}
6
+ {%- set audio_end_token = "<|object_ref_end|>" -%}
7
+ {%- for message in messages -%}
8
+ {%- if message['role'] == 'user' -%}
9
+ {{ '
10
+ ' }}<|im_start|>user{{ '
11
+ ' }}{%- set text_items = message['content'] | selectattr('type', 'equalto', 'text') | list -%}
12
+ {%- set context_text = text_items[0]['text'] if text_items else none -%}
13
+ {%- for item in message['content'] -%}
14
+ {%- if item['type'] == 'audio' -%}
15
+ {{ audio_start_token }}{{ audio_token }}{{ audio_end_token }}{{ "
16
+ " }}{%- if context_text -%}
17
+ This is a <|AUDIO_DURATION|> seconds audio, with extra info: {{ context_text }}
18
+
19
+ Please transcribe it with these keys: Start time, End time, Speaker ID, Content{%- else -%}
20
+ This is a <|AUDIO_DURATION|> seconds audio, please transcribe it with these keys: Start time, End time, Speaker ID, Content{%- endif -%}
21
+ {%- endif -%}
22
+ {%- endfor -%}
23
+ <|im_end|>{{ '
24
+ ' }}
25
+ {%- endif -%}
26
+ {%- endfor -%}
config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "acoustic_tokenizer_chunk_size": 1440000,
3
+ "acoustic_tokenizer_encoder_config": {
4
+ "channels": 1,
5
+ "depths": [
6
+ 3,
7
+ 3,
8
+ 3,
9
+ 3,
10
+ 3,
11
+ 3,
12
+ 8
13
+ ],
14
+ "downsampling_ratios": [
15
+ 2,
16
+ 2,
17
+ 4,
18
+ 5,
19
+ 5,
20
+ 8
21
+ ],
22
+ "dtype": "bfloat16",
23
+ "ffn_expansion": 4,
24
+ "hidden_act": "gelu",
25
+ "hidden_size": 64,
26
+ "initializer_range": 0.01,
27
+ "kernel_size": 7,
28
+ "layer_scale_init_value": 1e-06,
29
+ "model_type": "vibevoice_acoustic_tokenizer_encoder",
30
+ "num_filters": 32,
31
+ "rms_norm_eps": 1e-05,
32
+ "vae_std": 0.625,
33
+ "weight_init_value": 0.01
34
+ },
35
+ "architectures": [
36
+ "VibeVoiceAsrForConditionalGeneration"
37
+ ],
38
+ "audio_bos_token_id": 151646,
39
+ "audio_eos_token_id": 151647,
40
+ "audio_token_id": 151648,
41
+ "dtype": "bfloat16",
42
+ "model_type": "vibevoice_asr",
43
+ "semantic_tokenizer_encoder_config": {
44
+ "channels": 1,
45
+ "depths": [
46
+ 3,
47
+ 3,
48
+ 3,
49
+ 3,
50
+ 3,
51
+ 3,
52
+ 8
53
+ ],
54
+ "downsampling_ratios": [
55
+ 2,
56
+ 2,
57
+ 4,
58
+ 5,
59
+ 5,
60
+ 8
61
+ ],
62
+ "dtype": "bfloat16",
63
+ "ffn_expansion": 4,
64
+ "hidden_act": "gelu",
65
+ "hidden_size": 128,
66
+ "initializer_range": 0.01,
67
+ "kernel_size": 7,
68
+ "layer_scale_init_value": 1e-06,
69
+ "model_type": "vibevoice_acoustic_tokenizer_encoder",
70
+ "num_filters": 32,
71
+ "rms_norm_eps": 1e-05,
72
+ "vae_std": 0.625,
73
+ "weight_init_value": 0.01
74
+ },
75
+ "text_config": {
76
+ "attention_dropout": 0.0,
77
+ "bos_token_id": null,
78
+ "dtype": "bfloat16",
79
+ "eos_token_id": null,
80
+ "hidden_act": "silu",
81
+ "hidden_size": 3584,
82
+ "initializer_range": 0.02,
83
+ "intermediate_size": 18944,
84
+ "layer_types": [
85
+ "full_attention",
86
+ "full_attention",
87
+ "full_attention",
88
+ "full_attention",
89
+ "full_attention",
90
+ "full_attention",
91
+ "full_attention",
92
+ "full_attention",
93
+ "full_attention",
94
+ "full_attention",
95
+ "full_attention",
96
+ "full_attention",
97
+ "full_attention",
98
+ "full_attention",
99
+ "full_attention",
100
+ "full_attention",
101
+ "full_attention",
102
+ "full_attention",
103
+ "full_attention",
104
+ "full_attention",
105
+ "full_attention",
106
+ "full_attention",
107
+ "full_attention",
108
+ "full_attention",
109
+ "full_attention",
110
+ "full_attention",
111
+ "full_attention",
112
+ "full_attention"
113
+ ],
114
+ "max_position_embeddings": 131072,
115
+ "max_window_layers": 28,
116
+ "model_type": "qwen2",
117
+ "num_attention_heads": 28,
118
+ "num_hidden_layers": 28,
119
+ "num_key_value_heads": 4,
120
+ "pad_token_id": null,
121
+ "rms_norm_eps": 1e-06,
122
+ "rope_parameters": {
123
+ "rope_theta": 1000000.0,
124
+ "rope_type": "default"
125
+ },
126
+ "sliding_window": null,
127
+ "tie_word_embeddings": false,
128
+ "use_cache": true,
129
+ "use_mrope": false,
130
+ "use_sliding_window": false,
131
+ "vocab_size": 152064
132
+ },
133
+ "transformers_version": "5.3.0.dev0",
134
+ "vocab_size": 500
135
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "do_sample": false,
4
+ "eos_token_id": 151643,
5
+ "max_length": 32768,
6
+ "max_new_tokens": 32768,
7
+ "output_attentions": false,
8
+ "output_hidden_states": false,
9
+ "pad_token_id": 151655,
10
+ "transformers_version": "5.3.0.dev0",
11
+ "use_cache": true
12
+ }
processor_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_bos_token": "<|object_ref_start|>",
3
+ "audio_duration_token": "<|AUDIO_DURATION|>",
4
+ "audio_eos_token": "<|object_ref_end|>",
5
+ "audio_token": "<|box_start|>",
6
+ "feature_extractor": {
7
+ "eps": 1e-06,
8
+ "feature_extractor_type": "VibeVoiceAcousticTokenizerFeatureExtractor",
9
+ "feature_size": 1,
10
+ "normalize_audio": true,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "return_attention_mask": true,
14
+ "sampling_rate": 24000,
15
+ "target_dB_FS": -25
16
+ },
17
+ "processor_class": "VibeVoiceAsrProcessor"
18
+ }
tokenizer.json ADDED
@@ -0,0 +1,1729 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "normalizer": {
206
+ "type": "NFC"
207
+ },
208
+ "pre_tokenizer": {
209
+ "type": "Sequence",
210
+ "pretokenizers": [
211
+ {
212
+ "type": "Split",
213
+ "pattern": {
214
+ "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+"
215
+ },
216
+ "behavior": "Isolated",
217
+ "invert": false
218
+ },
219
+ {
220
+ "type": "ByteLevel",
221
+ "add_prefix_space": false,
222
+ "trim_offsets": true,
223
+ "use_regex": false
224
+ }
225
+ ]
226
+ },
227
+ "post_processor": {
228
+ "type": "ByteLevel",
229
+ "add_prefix_space": false,
230
+ "trim_offsets": false,
231
+ "use_regex": false
232
+ },
233
+ "decoder": {
234
+ "type": "ByteLevel",
235
+ "add_prefix_space": true,
236
+ "trim_offsets": true,
237
+ "use_regex": true
238
+ },
239
+ "model": {
240
+ "type": "BPE",
241
+ "dropout": null,
242
+ "unk_token": null,
243
+ "continuing_subword_prefix": "",
244
+ "end_of_word_suffix": "",
245
+ "fuse_unk": false,
246
+ "byte_fallback": false,
247
+ "ignore_merges": false,
248
+ "vocab": {
249
+ "!": 0,
250
+ "\"": 1,
251
+ "#": 2,
252
+ "$": 3,
253
+ "%": 4,
254
+ "&": 5,
255
+ "'": 6,
256
+ "(": 7,
257
+ ")": 8,
258
+ "*": 9,
259
+ "+": 10,
260
+ ",": 11,
261
+ "-": 12,
262
+ ".": 13,
263
+ "/": 14,
264
+ "0": 15,
265
+ "1": 16,
266
+ "2": 17,
267
+ "3": 18,
268
+ "4": 19,
269
+ "5": 20,
270
+ "6": 21,
271
+ "7": 22,
272
+ "8": 23,
273
+ "9": 24,
274
+ ":": 25,
275
+ ";": 26,
276
+ "<": 27,
277
+ "=": 28,
278
+ ">": 29,
279
+ "?": 30,
280
+ "@": 31,
281
+ "A": 32,
282
+ "B": 33,
283
+ "C": 34,
284
+ "D": 35,
285
+ "E": 36,
286
+ "F": 37,
287
+ "G": 38,
288
+ "H": 39,
289
+ "I": 40,
290
+ "J": 41,
291
+ "K": 42,
292
+ "L": 43,
293
+ "M": 44,
294
+ "N": 45,
295
+ "O": 46,
296
+ "P": 47,
297
+ "Q": 48,
298
+ "R": 49,
299
+ "S": 50,
300
+ "T": 51,
301
+ "U": 52,
302
+ "V": 53,
303
+ "W": 54,
304
+ "X": 55,
305
+ "Y": 56,
306
+ "Z": 57,
307
+ "[": 58,
308
+ "\\": 59,
309
+ "]": 60,
310
+ "^": 61,
311
+ "_": 62,
312
+ "`": 63,
313
+ "a": 64,
314
+ "b": 65,
315
+ "c": 66,
316
+ "d": 67,
317
+ "e": 68,
318
+ "f": 69,
319
+ "g": 70,
320
+ "h": 71,
321
+ "i": 72,
322
+ "j": 73,
323
+ "k": 74,
324
+ "l": 75,
325
+ "m": 76,
326
+ "n": 77,
327
+ "o": 78,
328
+ "p": 79,
329
+ "q": 80,
330
+ "r": 81,
331
+ "s": 82,
332
+ "t": 83,
333
+ "u": 84,
334
+ "v": 85,
335
+ "w": 86,
336
+ "x": 87,
337
+ "y": 88,
338
+ "z": 89,
339
+ "{": 90,
340
+ "|": 91,
341
+ "}": 92,
342
+ "~": 93,
343
+ "¡": 94,
344
+ "¢": 95,
345
+ "£": 96,
346
+ "¤": 97,
347
+ "¥": 98,
348
+ "¦": 99,
349
+ "§": 100,
350
+ "¨": 101,
351
+ "©": 102,
352
+ "ª": 103,
353
+ "«": 104,
354
+ "¬": 105,
355
+ "®": 106,
356
+ "¯": 107,
357
+ "°": 108,
358
+ "±": 109,
359
+ "²": 110,
360
+ "³": 111,
361
+ "´": 112,
362
+ "µ": 113,
363
+ "¶": 114,
364
+ "·": 115,
365
+ "¸": 116,
366
+ "¹": 117,
367
+ "º": 118,
368
+ "»": 119,
369
+ "¼": 120,
370
+ "½": 121,
371
+ "¾": 122,
372
+ "¿": 123,
373
+ "À": 124,
374
+ "Á": 125,
375
+ "Â": 126,
376
+ "Ã": 127,
377
+ "Ä": 128,
378
+ "Å": 129,
379
+ "Æ": 130,
380
+ "Ç": 131,
381
+ "È": 132,
382
+ "É": 133,
383
+ "Ê": 134,
384
+ "Ë": 135,
385
+ "Ì": 136,
386
+ "Í": 137,
387
+ "Î": 138,
388
+ "Ï": 139,
389
+ "Ð": 140,
390
+ "Ñ": 141,
391
+ "Ò": 142,
392
+ "Ó": 143,
393
+ "Ô": 144,
394
+ "Õ": 145,
395
+ "Ö": 146,
396
+ "×": 147,
397
+ "Ø": 148,
398
+ "Ù": 149,
399
+ "Ú": 150,
400
+ "Û": 151,
401
+ "Ü": 152,
402
+ "Ý": 153,
403
+ "Þ": 154,
404
+ "ß": 155,
405
+ "à": 156,
406
+ "á": 157,
407
+ "â": 158,
408
+ "ã": 159,
409
+ "ä": 160,
410
+ "å": 161,
411
+ "æ": 162,
412
+ "ç": 163,
413
+ "è": 164,
414
+ "é": 165,
415
+ "ê": 166,
416
+ "ë": 167,
417
+ "ì": 168,
418
+ "í": 169,
419
+ "î": 170,
420
+ "ï": 171,
421
+ "ð": 172,
422
+ "ñ": 173,
423
+ "ò": 174,
424
+ "ó": 175,
425
+ "ô": 176,
426
+ "õ": 177,
427
+ "ö": 178,
428
+ "÷": 179,
429
+ "ø": 180,
430
+ "ù": 181,
431
+ "ú": 182,
432
+ "û": 183,
433
+ "ü": 184,
434
+ "ý": 185,
435
+ "þ": 186,
436
+ "ÿ": 187,
437
+ "Ā": 188,
438
+ "ā": 189,
439
+ "Ă": 190,
440
+ "ă": 191,
441
+ "Ą": 192,
442
+ "ą": 193,
443
+ "Ć": 194,
444
+ "ć": 195,
445
+ "Ĉ": 196,
446
+ "ĉ": 197,
447
+ "Ċ": 198,
448
+ "ċ": 199,
449
+ "Č": 200,
450
+ "č": 201,
451
+ "Ď": 202,
452
+ "ď": 203,
453
+ "Đ": 204,
454
+ "đ": 205,
455
+ "Ē": 206,
456
+ "ē": 207,
457
+ "Ĕ": 208,
458
+ "ĕ": 209,
459
+ "Ė": 210,
460
+ "ė": 211,
461
+ "Ę": 212,
462
+ "ę": 213,
463
+ "Ě": 214,
464
+ "ě": 215,
465
+ "Ĝ": 216,
466
+ "ĝ": 217,
467
+ "Ğ": 218,
468
+ "ğ": 219,
469
+ "Ġ": 220,
470
+ "ġ": 221,
471
+ "Ģ": 222,
472
+ "ģ": 223,
473
+ "Ĥ": 224,
474
+ "ĥ": 225,
475
+ "Ħ": 226,
476
+ "ħ": 227,
477
+ "Ĩ": 228,
478
+ "ĩ": 229,
479
+ "Ī": 230,
480
+ "ī": 231,
481
+ "Ĭ": 232,
482
+ "ĭ": 233,
483
+ "Į": 234,
484
+ "į": 235,
485
+ "İ": 236,
486
+ "ı": 237,
487
+ "IJ": 238,
488
+ "ij": 239,
489
+ "Ĵ": 240,
490
+ "ĵ": 241,
491
+ "Ķ": 242,
492
+ "ķ": 243,
493
+ "ĸ": 244,
494
+ "Ĺ": 245,
495
+ "ĺ": 246,
496
+ "Ļ": 247,
497
+ "ļ": 248,
498
+ "Ľ": 249,
499
+ "ľ": 250,
500
+ "Ŀ": 251,
501
+ "ŀ": 252,
502
+ "Ł": 253,
503
+ "ł": 254,
504
+ "Ń": 255,
505
+ "ĠĠ": 256,
506
+ "ĠĠĠĠ": 257,
507
+ "in": 258,
508
+ "Ġt": 259,
509
+ "ĠĠĠĠĠĠĠĠ": 260,
510
+ "er": 261,
511
+ "ĠĠĠ": 262,
512
+ "on": 263,
513
+ "Ġa": 264,
514
+ "re": 265,
515
+ "at": 266,
516
+ "st": 267,
517
+ "en": 268,
518
+ "or": 269,
519
+ "Ġth": 270,
520
+ "ĊĊ": 271,
521
+ "Ġc": 272,
522
+ "le": 273,
523
+ "Ġs": 274,
524
+ "it": 275,
525
+ "an": 276,
526
+ "ar": 277,
527
+ "al": 278,
528
+ "Ġthe": 279,
529
+ ";Ċ": 280,
530
+ "Ġp": 281,
531
+ "Ġf": 282,
532
+ "ou": 283,
533
+ "Ġ=": 284,
534
+ "is": 285,
535
+ "ĠĠĠĠĠĠĠ": 286,
536
+ "ing": 287,
537
+ "es": 288,
538
+ "Ġw": 289,
539
+ "ion": 290,
540
+ "ed": 291,
541
+ "ic": 292,
542
+ "Ġb": 293,
543
+ "Ġd": 294,
544
+ "et": 295,
545
+ "Ġm": 296,
546
+ "Ġo": 297,
547
+ "ĉĉ": 298,
548
+ "ro": 299,
549
+ "as": 300,
550
+ "el": 301,
551
+ "ct": 302,
552
+ "nd": 303,
553
+ "Ġin": 304,
554
+ "Ġh": 305,
555
+ "ent": 306,
556
+ "id": 307,
557
+ "Ġn": 308,
558
+ "am": 309,
559
+ "ĠĠĠĠĠĠĠĠĠĠĠ": 310,
560
+ "Ġto": 311,
561
+ "Ġre": 312,
562
+ "--": 313,
563
+ "Ġ{": 314,
564
+ "Ġof": 315,
565
+ "om": 316,
566
+ ");Ċ": 317,
567
+ "im": 318,
568
+ "čĊ": 319,
569
+ "Ġ(": 320,
570
+ "il": 321,
571
+ "//": 322,
572
+ "Ġand": 323,
573
+ "ur": 324,
574
+ "se": 325,
575
+ "Ġl": 326,
576
+ "ex": 327,
577
+ "ĠS": 328,
578
+ "ad": 329,
579
+ "Ġ\"": 330,
580
+ "ch": 331,
581
+ "ut": 332,
582
+ "if": 333,
583
+ "**": 334,
584
+ "Ġ}": 335,
585
+ "em": 336,
586
+ "ol": 337,
587
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 338,
588
+ "th": 339,
589
+ ")Ċ": 340,
590
+ "Ġ{Ċ": 341,
591
+ "Ġg": 342,
592
+ "ig": 343,
593
+ "iv": 344,
594
+ ",Ċ": 345,
595
+ "ce": 346,
596
+ "od": 347,
597
+ "Ġv": 348,
598
+ "ate": 349,
599
+ "ĠT": 350,
600
+ "ag": 351,
601
+ "ay": 352,
602
+ "Ġ*": 353,
603
+ "ot": 354,
604
+ "us": 355,
605
+ "ĠC": 356,
606
+ "Ġst": 357,
607
+ "ĠI": 358,
608
+ "un": 359,
609
+ "ul": 360,
610
+ "ue": 361,
611
+ "ĠA": 362,
612
+ "ow": 363,
613
+ "Ġ'": 364,
614
+ "ew": 365,
615
+ "Ġ<": 366,
616
+ "ation": 367,
617
+ "()": 368,
618
+ "Ġfor": 369,
619
+ "ab": 370,
620
+ "ort": 371,
621
+ "um": 372,
622
+ "ame": 373,
623
+ "Ġis": 374,
624
+ "pe": 375,
625
+ "tr": 376,
626
+ "ck": 377,
627
+ "âĢ": 378,
628
+ "Ġy": 379,
629
+ "ist": 380,
630
+ "----": 381,
631
+ ".ĊĊ": 382,
632
+ "he": 383,
633
+ "Ġe": 384,
634
+ "lo": 385,
635
+ "ĠM": 386,
636
+ "Ġbe": 387,
637
+ "ers": 388,
638
+ "Ġon": 389,
639
+ "Ġcon": 390,
640
+ "ap": 391,
641
+ "ub": 392,
642
+ "ĠP": 393,
643
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 394,
644
+ "ass": 395,
645
+ "int": 396,
646
+ ">Ċ": 397,
647
+ "ly": 398,
648
+ "urn": 399,
649
+ "Ġ$": 400,
650
+ ";ĊĊ": 401,
651
+ "av": 402,
652
+ "port": 403,
653
+ "ir": 404,
654
+ "->": 405,
655
+ "nt": 406,
656
+ "ction": 407,
657
+ "end": 408,
658
+ "Ġde": 409,
659
+ "ith": 410,
660
+ "out": 411,
661
+ "turn": 412,
662
+ "our": 413,
663
+ "ĠĠĠĠĠ": 414,
664
+ "lic": 415,
665
+ "res": 416,
666
+ "pt": 417,
667
+ "==": 418,
668
+ "Ġthis": 419,
669
+ "Ġwh": 420,
670
+ "Ġif": 421,
671
+ "ĠD": 422,
672
+ "ver": 423,
673
+ "age": 424,
674
+ "ĠB": 425,
675
+ "ht": 426,
676
+ "ext": 427,
677
+ "=\"": 428,
678
+ "Ġthat": 429,
679
+ "****": 430,
680
+ "ĠR": 431,
681
+ "Ġit": 432,
682
+ "ess": 433,
683
+ "ĠF": 434,
684
+ "Ġr": 435,
685
+ "os": 436,
686
+ "and": 437,
687
+ "Ġas": 438,
688
+ "ect": 439,
689
+ "ke": 440,
690
+ "rom": 441,
691
+ "Ġ//": 442,
692
+ "con": 443,
693
+ "ĠL": 444,
694
+ "(\"": 445,
695
+ "qu": 446,
696
+ "lass": 447,
697
+ "Ġwith": 448,
698
+ "iz": 449,
699
+ "de": 450,
700
+ "ĠN": 451,
701
+ "Ġal": 452,
702
+ "op": 453,
703
+ "up": 454,
704
+ "get": 455,
705
+ "Ġ}Ċ": 456,
706
+ "ile": 457,
707
+ "Ġan": 458,
708
+ "ata": 459,
709
+ "ore": 460,
710
+ "ri": 461,
711
+ "Ġpro": 462,
712
+ ";čĊ": 463,
713
+ "ĉĉĉĉ": 464,
714
+ "ter": 465,
715
+ "ain": 466,
716
+ "ĠW": 467,
717
+ "ĠE": 468,
718
+ "Ġcom": 469,
719
+ "Ġreturn": 470,
720
+ "art": 471,
721
+ "ĠH": 472,
722
+ "ack": 473,
723
+ "import": 474,
724
+ "ublic": 475,
725
+ "Ġor": 476,
726
+ "est": 477,
727
+ "ment": 478,
728
+ "ĠG": 479,
729
+ "able": 480,
730
+ "Ġ-": 481,
731
+ "ine": 482,
732
+ "ill": 483,
733
+ "ind": 484,
734
+ "ere": 485,
735
+ "::": 486,
736
+ "ity": 487,
737
+ "Ġ+": 488,
738
+ "Ġtr": 489,
739
+ "elf": 490,
740
+ "ight": 491,
741
+ "('": 492,
742
+ "orm": 493,
743
+ "ult": 494,
744
+ "str": 495,
745
+ "..": 496,
746
+ "\",": 497,
747
+ "Ġyou": 498,
748
+ "ype": 499
749
+ },
750
+ "merges": [
751
+ [
752
+ "Ġ",
753
+ "Ġ"
754
+ ],
755
+ [
756
+ "ĠĠ",
757
+ "ĠĠ"
758
+ ],
759
+ [
760
+ "i",
761
+ "n"
762
+ ],
763
+ [
764
+ "Ġ",
765
+ "t"
766
+ ],
767
+ [
768
+ "ĠĠĠĠ",
769
+ "ĠĠĠĠ"
770
+ ],
771
+ [
772
+ "e",
773
+ "r"
774
+ ],
775
+ [
776
+ "ĠĠ",
777
+ "Ġ"
778
+ ],
779
+ [
780
+ "o",
781
+ "n"
782
+ ],
783
+ [
784
+ "Ġ",
785
+ "a"
786
+ ],
787
+ [
788
+ "r",
789
+ "e"
790
+ ],
791
+ [
792
+ "a",
793
+ "t"
794
+ ],
795
+ [
796
+ "s",
797
+ "t"
798
+ ],
799
+ [
800
+ "e",
801
+ "n"
802
+ ],
803
+ [
804
+ "o",
805
+ "r"
806
+ ],
807
+ [
808
+ "Ġt",
809
+ "h"
810
+ ],
811
+ [
812
+ "Ċ",
813
+ "Ċ"
814
+ ],
815
+ [
816
+ "Ġ",
817
+ "c"
818
+ ],
819
+ [
820
+ "l",
821
+ "e"
822
+ ],
823
+ [
824
+ "Ġ",
825
+ "s"
826
+ ],
827
+ [
828
+ "i",
829
+ "t"
830
+ ],
831
+ [
832
+ "a",
833
+ "n"
834
+ ],
835
+ [
836
+ "a",
837
+ "r"
838
+ ],
839
+ [
840
+ "a",
841
+ "l"
842
+ ],
843
+ [
844
+ "Ġth",
845
+ "e"
846
+ ],
847
+ [
848
+ ";",
849
+ "Ċ"
850
+ ],
851
+ [
852
+ "Ġ",
853
+ "p"
854
+ ],
855
+ [
856
+ "Ġ",
857
+ "f"
858
+ ],
859
+ [
860
+ "o",
861
+ "u"
862
+ ],
863
+ [
864
+ "Ġ",
865
+ "="
866
+ ],
867
+ [
868
+ "i",
869
+ "s"
870
+ ],
871
+ [
872
+ "ĠĠĠĠ",
873
+ "ĠĠĠ"
874
+ ],
875
+ [
876
+ "in",
877
+ "g"
878
+ ],
879
+ [
880
+ "e",
881
+ "s"
882
+ ],
883
+ [
884
+ "Ġ",
885
+ "w"
886
+ ],
887
+ [
888
+ "i",
889
+ "on"
890
+ ],
891
+ [
892
+ "e",
893
+ "d"
894
+ ],
895
+ [
896
+ "i",
897
+ "c"
898
+ ],
899
+ [
900
+ "Ġ",
901
+ "b"
902
+ ],
903
+ [
904
+ "Ġ",
905
+ "d"
906
+ ],
907
+ [
908
+ "e",
909
+ "t"
910
+ ],
911
+ [
912
+ "Ġ",
913
+ "m"
914
+ ],
915
+ [
916
+ "Ġ",
917
+ "o"
918
+ ],
919
+ [
920
+ "ĉ",
921
+ "ĉ"
922
+ ],
923
+ [
924
+ "r",
925
+ "o"
926
+ ],
927
+ [
928
+ "a",
929
+ "s"
930
+ ],
931
+ [
932
+ "e",
933
+ "l"
934
+ ],
935
+ [
936
+ "c",
937
+ "t"
938
+ ],
939
+ [
940
+ "n",
941
+ "d"
942
+ ],
943
+ [
944
+ "Ġ",
945
+ "in"
946
+ ],
947
+ [
948
+ "Ġ",
949
+ "h"
950
+ ],
951
+ [
952
+ "en",
953
+ "t"
954
+ ],
955
+ [
956
+ "i",
957
+ "d"
958
+ ],
959
+ [
960
+ "Ġ",
961
+ "n"
962
+ ],
963
+ [
964
+ "a",
965
+ "m"
966
+ ],
967
+ [
968
+ "ĠĠĠĠĠĠĠĠ",
969
+ "ĠĠĠ"
970
+ ],
971
+ [
972
+ "Ġt",
973
+ "o"
974
+ ],
975
+ [
976
+ "Ġ",
977
+ "re"
978
+ ],
979
+ [
980
+ "-",
981
+ "-"
982
+ ],
983
+ [
984
+ "Ġ",
985
+ "{"
986
+ ],
987
+ [
988
+ "Ġo",
989
+ "f"
990
+ ],
991
+ [
992
+ "o",
993
+ "m"
994
+ ],
995
+ [
996
+ ")",
997
+ ";Ċ"
998
+ ],
999
+ [
1000
+ "i",
1001
+ "m"
1002
+ ],
1003
+ [
1004
+ "č",
1005
+ "Ċ"
1006
+ ],
1007
+ [
1008
+ "Ġ",
1009
+ "("
1010
+ ],
1011
+ [
1012
+ "i",
1013
+ "l"
1014
+ ],
1015
+ [
1016
+ "/",
1017
+ "/"
1018
+ ],
1019
+ [
1020
+ "Ġa",
1021
+ "nd"
1022
+ ],
1023
+ [
1024
+ "u",
1025
+ "r"
1026
+ ],
1027
+ [
1028
+ "s",
1029
+ "e"
1030
+ ],
1031
+ [
1032
+ "Ġ",
1033
+ "l"
1034
+ ],
1035
+ [
1036
+ "e",
1037
+ "x"
1038
+ ],
1039
+ [
1040
+ "Ġ",
1041
+ "S"
1042
+ ],
1043
+ [
1044
+ "a",
1045
+ "d"
1046
+ ],
1047
+ [
1048
+ "Ġ",
1049
+ "\""
1050
+ ],
1051
+ [
1052
+ "c",
1053
+ "h"
1054
+ ],
1055
+ [
1056
+ "u",
1057
+ "t"
1058
+ ],
1059
+ [
1060
+ "i",
1061
+ "f"
1062
+ ],
1063
+ [
1064
+ "*",
1065
+ "*"
1066
+ ],
1067
+ [
1068
+ "Ġ",
1069
+ "}"
1070
+ ],
1071
+ [
1072
+ "e",
1073
+ "m"
1074
+ ],
1075
+ [
1076
+ "o",
1077
+ "l"
1078
+ ],
1079
+ [
1080
+ "ĠĠĠĠĠĠĠĠ",
1081
+ "ĠĠĠĠĠĠĠĠ"
1082
+ ],
1083
+ [
1084
+ "t",
1085
+ "h"
1086
+ ],
1087
+ [
1088
+ ")",
1089
+ "Ċ"
1090
+ ],
1091
+ [
1092
+ "Ġ{",
1093
+ "Ċ"
1094
+ ],
1095
+ [
1096
+ "Ġ",
1097
+ "g"
1098
+ ],
1099
+ [
1100
+ "i",
1101
+ "g"
1102
+ ],
1103
+ [
1104
+ "i",
1105
+ "v"
1106
+ ],
1107
+ [
1108
+ ",",
1109
+ "Ċ"
1110
+ ],
1111
+ [
1112
+ "c",
1113
+ "e"
1114
+ ],
1115
+ [
1116
+ "o",
1117
+ "d"
1118
+ ],
1119
+ [
1120
+ "Ġ",
1121
+ "v"
1122
+ ],
1123
+ [
1124
+ "at",
1125
+ "e"
1126
+ ],
1127
+ [
1128
+ "Ġ",
1129
+ "T"
1130
+ ],
1131
+ [
1132
+ "a",
1133
+ "g"
1134
+ ],
1135
+ [
1136
+ "a",
1137
+ "y"
1138
+ ],
1139
+ [
1140
+ "Ġ",
1141
+ "*"
1142
+ ],
1143
+ [
1144
+ "o",
1145
+ "t"
1146
+ ],
1147
+ [
1148
+ "u",
1149
+ "s"
1150
+ ],
1151
+ [
1152
+ "Ġ",
1153
+ "C"
1154
+ ],
1155
+ [
1156
+ "Ġ",
1157
+ "st"
1158
+ ],
1159
+ [
1160
+ "Ġ",
1161
+ "I"
1162
+ ],
1163
+ [
1164
+ "u",
1165
+ "n"
1166
+ ],
1167
+ [
1168
+ "u",
1169
+ "l"
1170
+ ],
1171
+ [
1172
+ "u",
1173
+ "e"
1174
+ ],
1175
+ [
1176
+ "Ġ",
1177
+ "A"
1178
+ ],
1179
+ [
1180
+ "o",
1181
+ "w"
1182
+ ],
1183
+ [
1184
+ "Ġ",
1185
+ "'"
1186
+ ],
1187
+ [
1188
+ "e",
1189
+ "w"
1190
+ ],
1191
+ [
1192
+ "Ġ",
1193
+ "<"
1194
+ ],
1195
+ [
1196
+ "at",
1197
+ "ion"
1198
+ ],
1199
+ [
1200
+ "(",
1201
+ ")"
1202
+ ],
1203
+ [
1204
+ "Ġf",
1205
+ "or"
1206
+ ],
1207
+ [
1208
+ "a",
1209
+ "b"
1210
+ ],
1211
+ [
1212
+ "or",
1213
+ "t"
1214
+ ],
1215
+ [
1216
+ "u",
1217
+ "m"
1218
+ ],
1219
+ [
1220
+ "am",
1221
+ "e"
1222
+ ],
1223
+ [
1224
+ "Ġ",
1225
+ "is"
1226
+ ],
1227
+ [
1228
+ "p",
1229
+ "e"
1230
+ ],
1231
+ [
1232
+ "t",
1233
+ "r"
1234
+ ],
1235
+ [
1236
+ "c",
1237
+ "k"
1238
+ ],
1239
+ [
1240
+ "â",
1241
+ "Ģ"
1242
+ ],
1243
+ [
1244
+ "Ġ",
1245
+ "y"
1246
+ ],
1247
+ [
1248
+ "i",
1249
+ "st"
1250
+ ],
1251
+ [
1252
+ "--",
1253
+ "--"
1254
+ ],
1255
+ [
1256
+ ".",
1257
+ "ĊĊ"
1258
+ ],
1259
+ [
1260
+ "h",
1261
+ "e"
1262
+ ],
1263
+ [
1264
+ "Ġ",
1265
+ "e"
1266
+ ],
1267
+ [
1268
+ "l",
1269
+ "o"
1270
+ ],
1271
+ [
1272
+ "Ġ",
1273
+ "M"
1274
+ ],
1275
+ [
1276
+ "Ġb",
1277
+ "e"
1278
+ ],
1279
+ [
1280
+ "er",
1281
+ "s"
1282
+ ],
1283
+ [
1284
+ "Ġ",
1285
+ "on"
1286
+ ],
1287
+ [
1288
+ "Ġc",
1289
+ "on"
1290
+ ],
1291
+ [
1292
+ "a",
1293
+ "p"
1294
+ ],
1295
+ [
1296
+ "u",
1297
+ "b"
1298
+ ],
1299
+ [
1300
+ "Ġ",
1301
+ "P"
1302
+ ],
1303
+ [
1304
+ "ĠĠĠĠĠĠĠĠ",
1305
+ "ĠĠĠĠĠĠĠ"
1306
+ ],
1307
+ [
1308
+ "as",
1309
+ "s"
1310
+ ],
1311
+ [
1312
+ "in",
1313
+ "t"
1314
+ ],
1315
+ [
1316
+ ">",
1317
+ "Ċ"
1318
+ ],
1319
+ [
1320
+ "l",
1321
+ "y"
1322
+ ],
1323
+ [
1324
+ "ur",
1325
+ "n"
1326
+ ],
1327
+ [
1328
+ "Ġ",
1329
+ "$"
1330
+ ],
1331
+ [
1332
+ ";",
1333
+ "ĊĊ"
1334
+ ],
1335
+ [
1336
+ "a",
1337
+ "v"
1338
+ ],
1339
+ [
1340
+ "p",
1341
+ "ort"
1342
+ ],
1343
+ [
1344
+ "i",
1345
+ "r"
1346
+ ],
1347
+ [
1348
+ "-",
1349
+ ">"
1350
+ ],
1351
+ [
1352
+ "n",
1353
+ "t"
1354
+ ],
1355
+ [
1356
+ "ct",
1357
+ "ion"
1358
+ ],
1359
+ [
1360
+ "en",
1361
+ "d"
1362
+ ],
1363
+ [
1364
+ "Ġd",
1365
+ "e"
1366
+ ],
1367
+ [
1368
+ "it",
1369
+ "h"
1370
+ ],
1371
+ [
1372
+ "ou",
1373
+ "t"
1374
+ ],
1375
+ [
1376
+ "t",
1377
+ "urn"
1378
+ ],
1379
+ [
1380
+ "ou",
1381
+ "r"
1382
+ ],
1383
+ [
1384
+ "ĠĠĠĠ",
1385
+ "Ġ"
1386
+ ],
1387
+ [
1388
+ "l",
1389
+ "ic"
1390
+ ],
1391
+ [
1392
+ "re",
1393
+ "s"
1394
+ ],
1395
+ [
1396
+ "p",
1397
+ "t"
1398
+ ],
1399
+ [
1400
+ "=",
1401
+ "="
1402
+ ],
1403
+ [
1404
+ "Ġth",
1405
+ "is"
1406
+ ],
1407
+ [
1408
+ "Ġw",
1409
+ "h"
1410
+ ],
1411
+ [
1412
+ "Ġ",
1413
+ "if"
1414
+ ],
1415
+ [
1416
+ "Ġ",
1417
+ "D"
1418
+ ],
1419
+ [
1420
+ "v",
1421
+ "er"
1422
+ ],
1423
+ [
1424
+ "ag",
1425
+ "e"
1426
+ ],
1427
+ [
1428
+ "Ġ",
1429
+ "B"
1430
+ ],
1431
+ [
1432
+ "h",
1433
+ "t"
1434
+ ],
1435
+ [
1436
+ "ex",
1437
+ "t"
1438
+ ],
1439
+ [
1440
+ "=",
1441
+ "\""
1442
+ ],
1443
+ [
1444
+ "Ġth",
1445
+ "at"
1446
+ ],
1447
+ [
1448
+ "**",
1449
+ "**"
1450
+ ],
1451
+ [
1452
+ "Ġ",
1453
+ "R"
1454
+ ],
1455
+ [
1456
+ "Ġ",
1457
+ "it"
1458
+ ],
1459
+ [
1460
+ "es",
1461
+ "s"
1462
+ ],
1463
+ [
1464
+ "Ġ",
1465
+ "F"
1466
+ ],
1467
+ [
1468
+ "Ġ",
1469
+ "r"
1470
+ ],
1471
+ [
1472
+ "o",
1473
+ "s"
1474
+ ],
1475
+ [
1476
+ "an",
1477
+ "d"
1478
+ ],
1479
+ [
1480
+ "Ġa",
1481
+ "s"
1482
+ ],
1483
+ [
1484
+ "e",
1485
+ "ct"
1486
+ ],
1487
+ [
1488
+ "k",
1489
+ "e"
1490
+ ],
1491
+ [
1492
+ "ro",
1493
+ "m"
1494
+ ],
1495
+ [
1496
+ "Ġ",
1497
+ "//"
1498
+ ],
1499
+ [
1500
+ "c",
1501
+ "on"
1502
+ ],
1503
+ [
1504
+ "Ġ",
1505
+ "L"
1506
+ ],
1507
+ [
1508
+ "(",
1509
+ "\""
1510
+ ],
1511
+ [
1512
+ "q",
1513
+ "u"
1514
+ ],
1515
+ [
1516
+ "l",
1517
+ "ass"
1518
+ ],
1519
+ [
1520
+ "Ġw",
1521
+ "ith"
1522
+ ],
1523
+ [
1524
+ "i",
1525
+ "z"
1526
+ ],
1527
+ [
1528
+ "d",
1529
+ "e"
1530
+ ],
1531
+ [
1532
+ "Ġ",
1533
+ "N"
1534
+ ],
1535
+ [
1536
+ "Ġa",
1537
+ "l"
1538
+ ],
1539
+ [
1540
+ "o",
1541
+ "p"
1542
+ ],
1543
+ [
1544
+ "u",
1545
+ "p"
1546
+ ],
1547
+ [
1548
+ "g",
1549
+ "et"
1550
+ ],
1551
+ [
1552
+ "Ġ}",
1553
+ "Ċ"
1554
+ ],
1555
+ [
1556
+ "i",
1557
+ "le"
1558
+ ],
1559
+ [
1560
+ "Ġa",
1561
+ "n"
1562
+ ],
1563
+ [
1564
+ "at",
1565
+ "a"
1566
+ ],
1567
+ [
1568
+ "o",
1569
+ "re"
1570
+ ],
1571
+ [
1572
+ "r",
1573
+ "i"
1574
+ ],
1575
+ [
1576
+ "Ġp",
1577
+ "ro"
1578
+ ],
1579
+ [
1580
+ ";",
1581
+ "čĊ"
1582
+ ],
1583
+ [
1584
+ "ĉĉ",
1585
+ "ĉĉ"
1586
+ ],
1587
+ [
1588
+ "t",
1589
+ "er"
1590
+ ],
1591
+ [
1592
+ "a",
1593
+ "in"
1594
+ ],
1595
+ [
1596
+ "Ġ",
1597
+ "W"
1598
+ ],
1599
+ [
1600
+ "Ġ",
1601
+ "E"
1602
+ ],
1603
+ [
1604
+ "Ġc",
1605
+ "om"
1606
+ ],
1607
+ [
1608
+ "Ġre",
1609
+ "turn"
1610
+ ],
1611
+ [
1612
+ "ar",
1613
+ "t"
1614
+ ],
1615
+ [
1616
+ "Ġ",
1617
+ "H"
1618
+ ],
1619
+ [
1620
+ "a",
1621
+ "ck"
1622
+ ],
1623
+ [
1624
+ "im",
1625
+ "port"
1626
+ ],
1627
+ [
1628
+ "ub",
1629
+ "lic"
1630
+ ],
1631
+ [
1632
+ "Ġ",
1633
+ "or"
1634
+ ],
1635
+ [
1636
+ "e",
1637
+ "st"
1638
+ ],
1639
+ [
1640
+ "m",
1641
+ "ent"
1642
+ ],
1643
+ [
1644
+ "Ġ",
1645
+ "G"
1646
+ ],
1647
+ [
1648
+ "ab",
1649
+ "le"
1650
+ ],
1651
+ [
1652
+ "Ġ",
1653
+ "-"
1654
+ ],
1655
+ [
1656
+ "in",
1657
+ "e"
1658
+ ],
1659
+ [
1660
+ "il",
1661
+ "l"
1662
+ ],
1663
+ [
1664
+ "in",
1665
+ "d"
1666
+ ],
1667
+ [
1668
+ "er",
1669
+ "e"
1670
+ ],
1671
+ [
1672
+ ":",
1673
+ ":"
1674
+ ],
1675
+ [
1676
+ "it",
1677
+ "y"
1678
+ ],
1679
+ [
1680
+ "Ġ",
1681
+ "+"
1682
+ ],
1683
+ [
1684
+ "Ġt",
1685
+ "r"
1686
+ ],
1687
+ [
1688
+ "el",
1689
+ "f"
1690
+ ],
1691
+ [
1692
+ "ig",
1693
+ "ht"
1694
+ ],
1695
+ [
1696
+ "(",
1697
+ "'"
1698
+ ],
1699
+ [
1700
+ "or",
1701
+ "m"
1702
+ ],
1703
+ [
1704
+ "ul",
1705
+ "t"
1706
+ ],
1707
+ [
1708
+ "st",
1709
+ "r"
1710
+ ],
1711
+ [
1712
+ ".",
1713
+ "."
1714
+ ],
1715
+ [
1716
+ "\"",
1717
+ ","
1718
+ ],
1719
+ [
1720
+ "Ġy",
1721
+ "ou"
1722
+ ],
1723
+ [
1724
+ "y",
1725
+ "pe"
1726
+ ]
1727
+ ]
1728
+ }
1729
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "model_max_length": 131072,
25
+ "pad_token": "<|endoftext|>",
26
+ "processor_class": "VibeVoiceAsrProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null,
30
+ "added_tokens_decoder": {
31
+ "500": {
32
+ "content": "<|endoftext|>",
33
+ "single_word": false,
34
+ "lstrip": false,
35
+ "rstrip": false,
36
+ "normalized": false,
37
+ "special": true
38
+ },
39
+ "501": {
40
+ "content": "<|im_start|>",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": false,
45
+ "special": true
46
+ },
47
+ "502": {
48
+ "content": "<|im_end|>",
49
+ "single_word": false,
50
+ "lstrip": false,
51
+ "rstrip": false,
52
+ "normalized": false,
53
+ "special": true
54
+ },
55
+ "503": {
56
+ "content": "<|object_ref_start|>",
57
+ "single_word": false,
58
+ "lstrip": false,
59
+ "rstrip": false,
60
+ "normalized": false,
61
+ "special": true
62
+ },
63
+ "504": {
64
+ "content": "<|object_ref_end|>",
65
+ "single_word": false,
66
+ "lstrip": false,
67
+ "rstrip": false,
68
+ "normalized": false,
69
+ "special": true
70
+ },
71
+ "505": {
72
+ "content": "<|box_start|>",
73
+ "single_word": false,
74
+ "lstrip": false,
75
+ "rstrip": false,
76
+ "normalized": false,
77
+ "special": true
78
+ },
79
+ "506": {
80
+ "content": "<|box_end|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ "507": {
88
+ "content": "<|quad_start|>",
89
+ "single_word": false,
90
+ "lstrip": false,
91
+ "rstrip": false,
92
+ "normalized": false,
93
+ "special": true
94
+ },
95
+ "508": {
96
+ "content": "<|quad_end|>",
97
+ "single_word": false,
98
+ "lstrip": false,
99
+ "rstrip": false,
100
+ "normalized": false,
101
+ "special": true
102
+ },
103
+ "509": {
104
+ "content": "<|vision_start|>",
105
+ "single_word": false,
106
+ "lstrip": false,
107
+ "rstrip": false,
108
+ "normalized": false,
109
+ "special": true
110
+ },
111
+ "510": {
112
+ "content": "<|vision_end|>",
113
+ "single_word": false,
114
+ "lstrip": false,
115
+ "rstrip": false,
116
+ "normalized": false,
117
+ "special": true
118
+ },
119
+ "511": {
120
+ "content": "<|vision_pad|>",
121
+ "single_word": false,
122
+ "lstrip": false,
123
+ "rstrip": false,
124
+ "normalized": false,
125
+ "special": true
126
+ },
127
+ "512": {
128
+ "content": "<|image_pad|>",
129
+ "single_word": false,
130
+ "lstrip": false,
131
+ "rstrip": false,
132
+ "normalized": false,
133
+ "special": true
134
+ },
135
+ "513": {
136
+ "content": "<|video_pad|>",
137
+ "single_word": false,
138
+ "lstrip": false,
139
+ "rstrip": false,
140
+ "normalized": false,
141
+ "special": true
142
+ },
143
+ "514": {
144
+ "content": "<tool_call>",
145
+ "single_word": false,
146
+ "lstrip": false,
147
+ "rstrip": false,
148
+ "normalized": false,
149
+ "special": false
150
+ },
151
+ "515": {
152
+ "content": "</tool_call>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": false
158
+ },
159
+ "516": {
160
+ "content": "<|fim_prefix|>",
161
+ "single_word": false,
162
+ "lstrip": false,
163
+ "rstrip": false,
164
+ "normalized": false,
165
+ "special": false
166
+ },
167
+ "517": {
168
+ "content": "<|fim_middle|>",
169
+ "single_word": false,
170
+ "lstrip": false,
171
+ "rstrip": false,
172
+ "normalized": false,
173
+ "special": false
174
+ },
175
+ "518": {
176
+ "content": "<|fim_suffix|>",
177
+ "single_word": false,
178
+ "lstrip": false,
179
+ "rstrip": false,
180
+ "normalized": false,
181
+ "special": false
182
+ },
183
+ "519": {
184
+ "content": "<|fim_pad|>",
185
+ "single_word": false,
186
+ "lstrip": false,
187
+ "rstrip": false,
188
+ "normalized": false,
189
+ "special": false
190
+ },
191
+ "520": {
192
+ "content": "<|repo_name|>",
193
+ "single_word": false,
194
+ "lstrip": false,
195
+ "rstrip": false,
196
+ "normalized": false,
197
+ "special": false
198
+ },
199
+ "521": {
200
+ "content": "<|file_sep|>",
201
+ "single_word": false,
202
+ "lstrip": false,
203
+ "rstrip": false,
204
+ "normalized": false,
205
+ "special": false
206
+ }
207
+ }
208
+ }