Hugging Face's logo

mlx-community
/
VoxCPM2-4bit

Text-to-Speech
Safetensors
MLX
mlx-audio
voxcpm2
tts
voice-cloning
voice-design
Model card Files
xet
 Community
acul3 commited on
Commit
2784721
·
verified ·
1 Parent(s): 27cfac3

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. config.json +220 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +81 -0
  5. test_en.wav +3 -0
  6. test_id.wav +3 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +212 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ test_en.wav filter=lfs diff=lfs merge=lfs -text
37
+ test_id.wav filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "voxcpm2",
3
+ "lm_config": {
4
+ "bos_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "hidden_size": 2048,
7
+ "intermediate_size": 6144,
8
+ "max_position_embeddings": 32768,
9
+ "num_attention_heads": 16,
10
+ "num_hidden_layers": 28,
11
+ "num_key_value_heads": 2,
12
+ "rms_norm_eps": 1e-05,
13
+ "rope_theta": 10000,
14
+ "kv_channels": 128,
15
+ "rope_scaling": {
16
+ "type": "longrope",
17
+ "long_factor": [
18
+ 0.9977997200264581,
19
+ 1.014658295992452,
20
+ 1.0349680404997148,
21
+ 1.059429246056193,
22
+ 1.0888815016813513,
23
+ 1.1243301355211495,
24
+ 1.166977103606075,
25
+ 1.2182568066927284,
26
+ 1.2798772354275727,
27
+ 1.3538666751582975,
28
+ 1.4426259039919596,
29
+ 1.5489853358570191,
30
+ 1.6762658237220625,
31
+ 1.8283407612492941,
32
+ 2.0096956085876183,
33
+ 2.225478927469756,
34
+ 2.481536379650452,
35
+ 2.784415934557119,
36
+ 3.1413289096347365,
37
+ 3.560047844772632,
38
+ 4.048719380066383,
39
+ 4.615569542115128,
40
+ 5.2684819496549835,
41
+ 6.014438591970396,
42
+ 6.858830049237097,
43
+ 7.804668263503327,
44
+ 8.851768731513417,
45
+ 9.99600492938444,
46
+ 11.228766118181639,
47
+ 12.536757560834843,
48
+ 13.902257701387796,
49
+ 15.303885189125953,
50
+ 16.717837610115794,
51
+ 18.119465097853947,
52
+ 19.484965238406907,
53
+ 20.792956681060105,
54
+ 22.02571786985731,
55
+ 23.16995406772833,
56
+ 24.217054535738416,
57
+ 25.16289275000465,
58
+ 26.007284207271347,
59
+ 26.753240849586767,
60
+ 27.40615325712662,
61
+ 27.973003419175363,
62
+ 28.461674954469114,
63
+ 28.880393889607006,
64
+ 29.237306864684626,
65
+ 29.540186419591297,
66
+ 29.79624387177199,
67
+ 30.01202719065413,
68
+ 30.193382037992453,
69
+ 30.34545697551969,
70
+ 30.47273746338473,
71
+ 30.579096895249787,
72
+ 30.66785612408345,
73
+ 30.741845563814174,
74
+ 30.80346599254902,
75
+ 30.85474569563567,
76
+ 30.897392663720595,
77
+ 30.932841297560394,
78
+ 30.962293553185553,
79
+ 30.986754758742034,
80
+ 31.007064503249293,
81
+ 31.02392307921529
82
+ ],
83
+ "short_factor": [
84
+ 0.9977997200264581,
85
+ 1.014658295992452,
86
+ 1.0349680404997148,
87
+ 1.059429246056193,
88
+ 1.0888815016813513,
89
+ 1.1243301355211495,
90
+ 1.166977103606075,
91
+ 1.2182568066927284,
92
+ 1.2798772354275727,
93
+ 1.3538666751582975,
94
+ 1.4426259039919596,
95
+ 1.5489853358570191,
96
+ 1.6762658237220625,
97
+ 1.8283407612492941,
98
+ 2.0096956085876183,
99
+ 2.225478927469756,
100
+ 2.481536379650452,
101
+ 2.784415934557119,
102
+ 3.1413289096347365,
103
+ 3.560047844772632,
104
+ 4.048719380066383,
105
+ 4.615569542115128,
106
+ 5.2684819496549835,
107
+ 6.014438591970396,
108
+ 6.858830049237097,
109
+ 7.804668263503327,
110
+ 8.851768731513417,
111
+ 9.99600492938444,
112
+ 11.228766118181639,
113
+ 12.536757560834843,
114
+ 13.902257701387796,
115
+ 15.303885189125953,
116
+ 16.717837610115794,
117
+ 18.119465097853947,
118
+ 19.484965238406907,
119
+ 20.792956681060105,
120
+ 22.02571786985731,
121
+ 23.16995406772833,
122
+ 24.217054535738416,
123
+ 25.16289275000465,
124
+ 26.007284207271347,
125
+ 26.753240849586767,
126
+ 27.40615325712662,
127
+ 27.973003419175363,
128
+ 28.461674954469114,
129
+ 28.880393889607006,
130
+ 29.237306864684626,
131
+ 29.540186419591297,
132
+ 29.79624387177199,
133
+ 30.01202719065413,
134
+ 30.193382037992453,
135
+ 30.34545697551969,
136
+ 30.47273746338473,
137
+ 30.579096895249787,
138
+ 30.66785612408345,
139
+ 30.741845563814174,
140
+ 30.80346599254902,
141
+ 30.85474569563567,
142
+ 30.897392663720595,
143
+ 30.932841297560394,
144
+ 30.962293553185553,
145
+ 30.986754758742034,
146
+ 31.007064503249293,
147
+ 31.02392307921529
148
+ ],
149
+ "original_max_position_embeddings": 32768
150
+ },
151
+ "vocab_size": 73448,
152
+ "use_mup": false,
153
+ "scale_emb": 12,
154
+ "dim_model_base": 256,
155
+ "scale_depth": 1.4
156
+ },
157
+ "patch_size": 4,
158
+ "feat_dim": 64,
159
+ "scalar_quantization_latent_dim": 512,
160
+ "scalar_quantization_scale": 9,
161
+ "residual_lm_num_layers": 8,
162
+ "residual_lm_no_rope": true,
163
+ "encoder_config": {
164
+ "hidden_dim": 1024,
165
+ "ffn_dim": 4096,
166
+ "num_heads": 16,
167
+ "num_layers": 12,
168
+ "kv_channels": 128
169
+ },
170
+ "dit_config": {
171
+ "hidden_dim": 1024,
172
+ "ffn_dim": 4096,
173
+ "num_heads": 16,
174
+ "num_layers": 12,
175
+ "kv_channels": 128,
176
+ "mean_mode": false,
177
+ "cfm_config": {
178
+ "sigma_min": 1e-06,
179
+ "solver": "euler",
180
+ "t_scheduler": "log-norm",
181
+ "inference_cfg_rate": 2.0
182
+ }
183
+ },
184
+ "audio_vae_config": {
185
+ "encoder_dim": 128,
186
+ "encoder_rates": [
187
+ 2,
188
+ 5,
189
+ 8,
190
+ 8
191
+ ],
192
+ "latent_dim": 64,
193
+ "decoder_dim": 2048,
194
+ "decoder_rates": [
195
+ 8,
196
+ 6,
197
+ 5,
198
+ 2,
199
+ 2,
200
+ 2
201
+ ],
202
+ "sr_bin_boundaries": [
203
+ 20000,
204
+ 30000,
205
+ 40000
206
+ ],
207
+ "sample_rate": 16000,
208
+ "out_sample_rate": 48000
209
+ },
210
+ "max_length": 8192,
211
+ "model_type": "voxcpm2",
212
+ "quantization": {
213
+ "bits": 4,
214
+ "group_size": 64,
215
+ "targets": [
216
+ "base_lm",
217
+ "residual_lm"
218
+ ]
219
+ }
220
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25bddc99a7cc6d28214f12dd676ed0afa9b0a805d6477f85c275bb113cb8acee
3
+ size 2297215329
special_tokens_map.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_end|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_start|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|tool_call|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<|execute_start|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<|execute_end|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<|fim_prefix|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<|fim_middle|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<|fim_suffix|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ }
59
+ ],
60
+ "bos_token": {
61
+ "content": "<s>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "eos_token": {
68
+ "content": "</s>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ },
74
+ "unk_token": {
75
+ "content": "<unk>",
76
+ "lstrip": false,
77
+ "normalized": false,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ }
81
+ }
test_en.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbfbc319e27a91d62b63c977830e58a0b2f08ea0fda73cb62e0f4294d3500dc9
3
+ size 522300
test_id.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b024780af7cb90d22c651ec9c2594c07d9bb5dcc9c9891c55e4032ef7f59ce97
3
+ size 614460
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "101": {
30
+ "content": "<|audio_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "102": {
38
+ "content": "<|audio_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "103": {
46
+ "content": "<|audio_prompt_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "104": {
54
+ "content": "<|audio_prompt_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "105": {
62
+ "content": "<|background|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "106": {
70
+ "content": "<|/background|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "107": {
78
+ "content": "<|characters|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "108": {
86
+ "content": "<|/characters|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "109": {
94
+ "content": "<|speaker_id|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "110": {
102
+ "content": "<|/speaker_id|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "111": {
110
+ "content": "<|span|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "112": {
118
+ "content": "<|/span|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "73440": {
126
+ "content": "<|im_end|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "73441": {
134
+ "content": "<|im_start|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "73442": {
142
+ "content": "<|tool_call|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "73443": {
150
+ "content": "<|execute_start|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "73444": {
158
+ "content": "<|execute_end|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "73445": {
166
+ "content": "<|fim_prefix|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "73446": {
174
+ "content": "<|fim_middle|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "73447": {
182
+ "content": "<|fim_suffix|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ }
189
+ },
190
+ "additional_special_tokens": [
191
+ "<|im_end|>",
192
+ "<|im_start|>",
193
+ "<|tool_call|>",
194
+ "<|execute_start|>",
195
+ "<|execute_end|>",
196
+ "<|fim_prefix|>",
197
+ "<|fim_middle|>",
198
+ "<|fim_suffix|>"
199
+ ],
200
+ "bos_token": "<s>",
201
+ "clean_up_tokenization_spaces": false,
202
+ "eos_token": "<|im_end|>",
203
+ "legacy": true,
204
+ "model_max_length": 1000000000000000019884624838656,
205
+ "pad_token": null,
206
+ "sp_model_kwargs": {},
207
+ "spaces_between_special_tokens": false,
208
+ "tokenizer_class": "LlamaTokenizer",
209
+ "unk_token": "<unk>",
210
+ "use_default_system_prompt": false,
211
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
212
+ }