Hugging Face's logo

mlx-community
/
VoxCPM1.5-6bit

Text-to-Speech
Safetensors
MLX
English
Chinese
voxcpm1.5
speech
speech generation
voice cloning
6-bit
Model card Files
xet
Community
prince-canuma commited on
Commit
e39f7e5
·
verified ·
1 Parent(s): b1048aa

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. README.md +29 -0
  2. config.json +148 -0
  3. model.safetensors +3 -0
  4. model.safetensors.index.json +0 -0
  5. special_tokens_map.json +81 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +212 -0
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - zh
6
+ base_model:
7
+ - openbmb/MiniCPM4-0.5B
8
+ pipeline_tag: text-to-speech
9
+ library_name: voxcpm1.5
10
+ tags:
11
+ - text-to-speech
12
+ - speech
13
+ - speech generation
14
+ - voice cloning
15
+ - mlx
16
+ ---
17
+
18
+ # mlx-community/VoxCPM1.5-6bit
19
+ This model was converted to MLX format from [`openbmb/VoxCPM1.5`](https://huggingface.co/openbmb/VoxCPM1.5) using mlx-audio version **0.2.7**.
20
+ Refer to the [original model card](https://huggingface.co/openbmb/VoxCPM1.5) for more details on the model.
21
+ ## Use with mlx
22
+
23
+ ```bash
24
+ pip install -U mlx-audio
25
+ ```
26
+
27
+ ```bash
28
+ python -m mlx_audio.tts.generate --model mlx-community/VoxCPM1.5-6bit --text "Describe this image."
29
+ ```
config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "voxcpm",
3
+ "audio_vae_config": {
4
+ "encoder_dim": 64,
5
+ "encoder_rates": [
6
+ 2,
7
+ 3,
8
+ 6,
9
+ 7,
10
+ 7
11
+ ],
12
+ "latent_dim": 64,
13
+ "decoder_dim": 2048,
14
+ "decoder_rates": [
15
+ 7,
16
+ 7,
17
+ 6,
18
+ 3,
19
+ 2
20
+ ],
21
+ "sample_rate": 44100
22
+ },
23
+ "device": "cuda",
24
+ "dit_config": {
25
+ "hidden_dim": 1024,
26
+ "ffn_dim": 4096,
27
+ "num_heads": 16,
28
+ "num_layers": 8,
29
+ "cfm_config": {
30
+ "sigma_min": 1e-06,
31
+ "solver": "euler",
32
+ "t_scheduler": "log-norm",
33
+ "inference_cfg_rate": 2.0
34
+ }
35
+ },
36
+ "dtype": "bfloat16",
37
+ "encoder_config": {
38
+ "hidden_dim": 1024,
39
+ "ffn_dim": 4096,
40
+ "num_heads": 16,
41
+ "num_layers": 8
42
+ },
43
+ "feat_dim": 64,
44
+ "lm_config": {
45
+ "bos_token_id": 1,
46
+ "eos_token_id": 2,
47
+ "hidden_size": 1024,
48
+ "intermediate_size": 4096,
49
+ "max_position_embeddings": 32768,
50
+ "num_attention_heads": 16,
51
+ "num_hidden_layers": 24,
52
+ "num_key_value_heads": 2,
53
+ "rms_norm_eps": 1e-05,
54
+ "rope_theta": 10000,
55
+ "rope_scaling": {
56
+ "type": "longrope",
57
+ "long_factor": [
58
+ 1.0004360675811768,
59
+ 1.0668443441390991,
60
+ 1.1631425619125366,
61
+ 1.3025742769241333,
62
+ 1.5040205717086792,
63
+ 1.7941505908966064,
64
+ 2.2101221084594727,
65
+ 2.802666664123535,
66
+ 3.6389970779418945,
67
+ 4.804192543029785,
68
+ 6.39855432510376,
69
+ 8.527148246765137,
70
+ 11.277542114257812,
71
+ 14.684998512268066,
72
+ 18.69317054748535,
73
+ 23.13019371032715,
74
+ 27.72362518310547,
75
+ 32.1606559753418,
76
+ 36.168827056884766,
77
+ 39.57627868652344,
78
+ 42.32667541503906,
79
+ 44.45526885986328,
80
+ 46.04962921142578,
81
+ 47.21482849121094,
82
+ 48.05115509033203,
83
+ 48.64370346069336,
84
+ 49.05967712402344,
85
+ 49.34980392456055,
86
+ 49.551246643066406,
87
+ 49.69068145751953,
88
+ 49.78697967529297,
89
+ 49.85338592529297
90
+ ],
91
+ "short_factor": [
92
+ 1.0004360675811768,
93
+ 1.0668443441390991,
94
+ 1.1631425619125366,
95
+ 1.3025742769241333,
96
+ 1.5040205717086792,
97
+ 1.7941505908966064,
98
+ 2.2101221084594727,
99
+ 2.802666664123535,
100
+ 3.6389970779418945,
101
+ 4.804192543029785,
102
+ 6.39855432510376,
103
+ 8.527148246765137,
104
+ 11.277542114257812,
105
+ 14.684998512268066,
106
+ 18.69317054748535,
107
+ 23.13019371032715,
108
+ 27.72362518310547,
109
+ 32.1606559753418,
110
+ 36.168827056884766,
111
+ 39.57627868652344,
112
+ 42.32667541503906,
113
+ 44.45526885986328,
114
+ 46.04962921142578,
115
+ 47.21482849121094,
116
+ 48.05115509033203,
117
+ 48.64370346069336,
118
+ 49.05967712402344,
119
+ 49.34980392456055,
120
+ 49.551246643066406,
121
+ 49.69068145751953,
122
+ 49.78697967529297,
123
+ 49.85338592529297
124
+ ],
125
+ "original_max_position_embeddings": 32768
126
+ },
127
+ "vocab_size": 73448,
128
+ "scale_emb": 12,
129
+ "dim_model_base": 256,
130
+ "scale_depth": 1.4,
131
+ "use_mup": false
132
+ },
133
+ "max_length": 8192,
134
+ "patch_size": 4,
135
+ "quantization": {
136
+ "group_size": 64,
137
+ "bits": 6,
138
+ "mode": "affine"
139
+ },
140
+ "quantization_config": {
141
+ "group_size": 64,
142
+ "bits": 6,
143
+ "mode": "affine"
144
+ },
145
+ "residual_lm_num_layers": 8,
146
+ "scalar_quantization_latent_dim": 256,
147
+ "scalar_quantization_scale": 9
148
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5c83684b36ab1c1add49dd320941859c21167ba7eb987e68e2307822796af5
3
+ size 823822876
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 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
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
+ }