Hugging Face's logo

InflexionLab
/
VibeVoice-ASR-Kazakh

Automatic Speech Recognition
VibeVoice
Safetensors
Kazakh
kazakh
lora
ksc2
Eval Results (legacy)
Model card Files
xet
 Community
diaslmb commited on
Commit
b37266a
·
verified ·
1 Parent(s): 1e5d304

Add VibeVoice-ASR fine-tuned on ISSAI KSC2 Kazakh dataset

Browse files
Files changed (13) hide show
  1. added_tokens.json +27 -0
  2. config.json +148 -0
  3. generation_config.json +4 -0
  4. merges.txt +0 -0
  5. model-00001-of-00004.safetensors +3 -0
  6. model-00002-of-00004.safetensors +3 -0
  7. model-00003-of-00004.safetensors +3 -0
  8. model-00004-of-00004.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. special_tokens_map.json +49 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +234 -0
  13. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_start|>": 151644,
4
+ "<|im_end|>": 151645,
5
+ "<|object_ref_start|>": 151646,
6
+ "<|object_ref_end|>": 151647,
7
+ "<|box_start|>": 151648,
8
+ "<|box_end|>": 151649,
9
+ "<|quad_start|>": 151650,
10
+ "<|quad_end|>": 151651,
11
+ "<|vision_start|>": 151652,
12
+ "<|vision_end|>": 151653,
13
+ "<|vision_pad|>": 151654,
14
+ "<|image_pad|>": 151655,
15
+ "<|video_pad|>": 151656,
16
+ "<tool_call>": 151657,
17
+ "</tool_call>": 151658,
18
+ "<|fim_prefix|>": 151659,
19
+ "<|fim_middle|>": 151660,
20
+ "<|fim_suffix|>": 151661,
21
+ "<|fim_pad|>": 151662,
22
+ "<|repo_name|>": 151663,
23
+ "<|file_sep|>": 151664,
24
+ "<|AUDIO|>": 151665,
25
+ "<|audio_bos|>": 151666,
26
+ "<|audio_eos|>": 151667
27
+ }
config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": false,
3
+ "acoustic_tokenizer_config": {
4
+ "causal": true,
5
+ "channels": 1,
6
+ "conv_bias": true,
7
+ "conv_norm": "none",
8
+ "corpus_normalize": 0.0,
9
+ "decoder_depths": null,
10
+ "decoder_n_filters": 32,
11
+ "decoder_ratios": [
12
+ 8,
13
+ 5,
14
+ 5,
15
+ 4,
16
+ 2,
17
+ 2
18
+ ],
19
+ "disable_last_norm": true,
20
+ "dtype": "bfloat16",
21
+ "encoder_depths": "3-3-3-3-3-3-8",
22
+ "encoder_n_filters": 32,
23
+ "encoder_ratios": [
24
+ 8,
25
+ 5,
26
+ 5,
27
+ 4,
28
+ 2,
29
+ 2
30
+ ],
31
+ "fix_std": 0.5,
32
+ "layer_scale_init_value": 1e-06,
33
+ "layernorm": "RMSNorm",
34
+ "layernorm_elementwise_affine": true,
35
+ "layernorm_eps": 1e-05,
36
+ "mixer_layer": "depthwise_conv",
37
+ "model_type": "vibevoice_acoustic_tokenizer",
38
+ "pad_mode": "constant",
39
+ "std_dist_type": "gaussian",
40
+ "vae_dim": 64,
41
+ "weight_init_value": 0.01
42
+ },
43
+ "acoustic_vae_dim": 64,
44
+ "architectures": [
45
+ "VibeVoiceForASRTraining"
46
+ ],
47
+ "decoder_config": {
48
+ "attention_dropout": 0.0,
49
+ "dtype": "bfloat16",
50
+ "hidden_act": "silu",
51
+ "hidden_size": 3584,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 18944,
54
+ "layer_types": [
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
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention",
81
+ "full_attention",
82
+ "full_attention"
83
+ ],
84
+ "max_position_embeddings": 131072,
85
+ "max_window_layers": 28,
86
+ "model_type": "qwen2",
87
+ "num_attention_heads": 28,
88
+ "num_hidden_layers": 28,
89
+ "num_key_value_heads": 4,
90
+ "rms_norm_eps": 1e-06,
91
+ "rope_scaling": null,
92
+ "rope_theta": 1000000.0,
93
+ "sliding_window": null,
94
+ "use_cache": true,
95
+ "use_mrope": false,
96
+ "use_sliding_window": false,
97
+ "vocab_size": 152064
98
+ },
99
+ "diffusion_head_config": {
100
+ "ddpm_batch_mul": 4,
101
+ "ddpm_beta_schedule": "cosine",
102
+ "ddpm_num_inference_steps": 20,
103
+ "ddpm_num_steps": 1000,
104
+ "diffusion_type": "ddpm",
105
+ "head_ffn_ratio": 3.0,
106
+ "head_layers": 4,
107
+ "hidden_size": 3584,
108
+ "latent_size": 64,
109
+ "model_type": "vibepod_diffusion_head",
110
+ "prediction_type": "v_prediction",
111
+ "rms_norm_eps": 1e-05,
112
+ "speech_vae_dim": 64
113
+ },
114
+ "dtype": "float32",
115
+ "model_type": "vibevoice",
116
+ "semantic_tokenizer_config": {
117
+ "causal": true,
118
+ "channels": 1,
119
+ "conv_bias": true,
120
+ "conv_norm": "none",
121
+ "corpus_normalize": 0.0,
122
+ "disable_last_norm": true,
123
+ "dtype": "bfloat16",
124
+ "encoder_depths": "3-3-3-3-3-3-8",
125
+ "encoder_n_filters": 32,
126
+ "encoder_ratios": [
127
+ 8,
128
+ 5,
129
+ 5,
130
+ 4,
131
+ 2,
132
+ 2
133
+ ],
134
+ "fix_std": 0,
135
+ "layer_scale_init_value": 1e-06,
136
+ "layernorm": "RMSNorm",
137
+ "layernorm_elementwise_affine": true,
138
+ "layernorm_eps": 1e-05,
139
+ "mixer_layer": "depthwise_conv",
140
+ "model_type": "vibevoice_semantic_tokenizer",
141
+ "pad_mode": "constant",
142
+ "std_dist_type": "none",
143
+ "vae_dim": 128,
144
+ "weight_init_value": 0.01
145
+ },
146
+ "semantic_vae_dim": 128,
147
+ "transformers_version": "4.57.6"
148
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.57.6"
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd989889041ca1f5c3e04d0c0cb2d7e6658d43bb88a75dc19a765fee3e65b3f
3
+ size 4877662336
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ba82980b772b4629ceb41ad2055f8320054eaa0fdff1226f8580ee36a0c822
3
+ size 4932752840
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17c1c50a94e57c558d09e9f51cc7f8d922964b30b5c067d67f7f53e2fb3b2c6
3
+ size 4982901128
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3698fd11a2597482d17b33ef28e21573755fb97541677d39f1eccdeb3802325
3
+ size 2554883402
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|AUDIO|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|audio_bos|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|audio_eos|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<|object_ref_start|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<|object_ref_end|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<|box_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ ],
46
+ "eos_token": "<|endoftext|>",
47
+ "pad_token": "<|endoftext|>",
48
+ "unk_token": "<|endoftext|>"
49
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<|AUDIO|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|audio_bos|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<|audio_eos|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ }
205
+ },
206
+ "additional_special_tokens": [
207
+ "<|im_start|>",
208
+ "<|im_end|>",
209
+ "<|object_ref_start|>",
210
+ "<|object_ref_end|>",
211
+ "<|box_start|>",
212
+ "<|box_end|>",
213
+ "<|quad_start|>",
214
+ "<|quad_end|>",
215
+ "<|vision_start|>",
216
+ "<|vision_end|>",
217
+ "<|vision_pad|>",
218
+ "<|image_pad|>",
219
+ "<|video_pad|>",
220
+ "<|AUDIO|>",
221
+ "<|audio_bos|>",
222
+ "<|audio_eos|>"
223
+ ],
224
+ "bos_token": null,
225
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {%- if messages[0]['content'] is string %}\n {{- messages[0]['content'] }}\n {%- else %}\n {%- for part in messages[0]['content'] %}\n {%- if part['type'] == 'text' %}\n {{- part['text'] }}\n {%- elif part['type'] == 'audio' or part['type'] == 'audio_url' %}\n {{- '<|AUDIO|>' }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['content'] is string %}\n {{- messages[0]['content'] }}\n {%- else %}\n {%- for part in messages[0]['content'] %}\n {%- if part['type'] == 'text' %}\n {{- part['text'] }}\n {%- elif part['type'] == 'audio' or part['type'] == 'audio_url' %}\n {{- '<|AUDIO|>' }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message['content'] is string %}\n {{- message['content'] }}\n {%- else %}\n {%- for part in message['content'] %}\n {%- if part['type'] == 'text' %}\n {{- part['text'] }}\n {%- elif part['type'] == 'audio' or part['type'] == 'audio_url' %}\n {{- '<|AUDIO|>' }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
226
+ "clean_up_tokenization_spaces": false,
227
+ "eos_token": "<|endoftext|>",
228
+ "errors": "replace",
229
+ "model_max_length": 131072,
230
+ "pad_token": "<|endoftext|>",
231
+ "split_special_tokens": false,
232
+ "tokenizer_class": "Qwen2Tokenizer",
233
+ "unk_token": null
234
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff