xinference 1.7.1__py3-none-any.whl → 1.8.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of xinference might be problematic. Click here for more details.

Files changed (136) hide show
  1. xinference/_version.py +3 -3
  2. xinference/client/restful/async_restful_client.py +8 -13
  3. xinference/client/restful/restful_client.py +6 -2
  4. xinference/core/chat_interface.py +6 -4
  5. xinference/core/media_interface.py +5 -0
  6. xinference/core/model.py +1 -5
  7. xinference/core/supervisor.py +117 -68
  8. xinference/core/worker.py +49 -37
  9. xinference/deploy/test/test_cmdline.py +2 -6
  10. xinference/model/audio/__init__.py +26 -23
  11. xinference/model/audio/chattts.py +3 -2
  12. xinference/model/audio/core.py +49 -98
  13. xinference/model/audio/cosyvoice.py +3 -2
  14. xinference/model/audio/custom.py +28 -73
  15. xinference/model/audio/f5tts.py +3 -2
  16. xinference/model/audio/f5tts_mlx.py +3 -2
  17. xinference/model/audio/fish_speech.py +3 -2
  18. xinference/model/audio/funasr.py +17 -4
  19. xinference/model/audio/kokoro.py +3 -2
  20. xinference/model/audio/megatts.py +3 -2
  21. xinference/model/audio/melotts.py +3 -2
  22. xinference/model/audio/model_spec.json +572 -171
  23. xinference/model/audio/utils.py +0 -6
  24. xinference/model/audio/whisper.py +3 -2
  25. xinference/model/audio/whisper_mlx.py +3 -2
  26. xinference/model/cache_manager.py +141 -0
  27. xinference/model/core.py +6 -49
  28. xinference/model/custom.py +174 -0
  29. xinference/model/embedding/__init__.py +67 -56
  30. xinference/model/embedding/cache_manager.py +35 -0
  31. xinference/model/embedding/core.py +104 -84
  32. xinference/model/embedding/custom.py +55 -78
  33. xinference/model/embedding/embed_family.py +80 -31
  34. xinference/model/embedding/flag/core.py +21 -5
  35. xinference/model/embedding/llama_cpp/__init__.py +0 -0
  36. xinference/model/embedding/llama_cpp/core.py +234 -0
  37. xinference/model/embedding/model_spec.json +968 -103
  38. xinference/model/embedding/sentence_transformers/core.py +30 -20
  39. xinference/model/embedding/vllm/core.py +11 -5
  40. xinference/model/flexible/__init__.py +8 -2
  41. xinference/model/flexible/core.py +26 -119
  42. xinference/model/flexible/custom.py +69 -0
  43. xinference/model/flexible/launchers/image_process_launcher.py +1 -0
  44. xinference/model/flexible/launchers/modelscope_launcher.py +5 -1
  45. xinference/model/flexible/launchers/transformers_launcher.py +15 -3
  46. xinference/model/flexible/launchers/yolo_launcher.py +5 -1
  47. xinference/model/image/__init__.py +20 -20
  48. xinference/model/image/cache_manager.py +62 -0
  49. xinference/model/image/core.py +70 -182
  50. xinference/model/image/custom.py +28 -72
  51. xinference/model/image/model_spec.json +402 -119
  52. xinference/model/image/ocr/got_ocr2.py +3 -2
  53. xinference/model/image/stable_diffusion/core.py +22 -7
  54. xinference/model/image/stable_diffusion/mlx.py +6 -6
  55. xinference/model/image/utils.py +2 -2
  56. xinference/model/llm/__init__.py +71 -94
  57. xinference/model/llm/cache_manager.py +292 -0
  58. xinference/model/llm/core.py +37 -111
  59. xinference/model/llm/custom.py +88 -0
  60. xinference/model/llm/llama_cpp/core.py +5 -7
  61. xinference/model/llm/llm_family.json +16260 -8151
  62. xinference/model/llm/llm_family.py +138 -839
  63. xinference/model/llm/lmdeploy/core.py +5 -7
  64. xinference/model/llm/memory.py +3 -4
  65. xinference/model/llm/mlx/core.py +6 -8
  66. xinference/model/llm/reasoning_parser.py +3 -1
  67. xinference/model/llm/sglang/core.py +32 -14
  68. xinference/model/llm/transformers/chatglm.py +3 -7
  69. xinference/model/llm/transformers/core.py +49 -27
  70. xinference/model/llm/transformers/deepseek_v2.py +2 -2
  71. xinference/model/llm/transformers/gemma3.py +2 -2
  72. xinference/model/llm/transformers/multimodal/cogagent.py +2 -2
  73. xinference/model/llm/transformers/multimodal/deepseek_vl2.py +2 -2
  74. xinference/model/llm/transformers/multimodal/gemma3.py +2 -2
  75. xinference/model/llm/transformers/multimodal/glm4_1v.py +167 -0
  76. xinference/model/llm/transformers/multimodal/glm4v.py +2 -2
  77. xinference/model/llm/transformers/multimodal/intern_vl.py +2 -2
  78. xinference/model/llm/transformers/multimodal/minicpmv26.py +3 -3
  79. xinference/model/llm/transformers/multimodal/ovis2.py +2 -2
  80. xinference/model/llm/transformers/multimodal/qwen-omni.py +2 -2
  81. xinference/model/llm/transformers/multimodal/qwen2_audio.py +2 -2
  82. xinference/model/llm/transformers/multimodal/qwen2_vl.py +2 -2
  83. xinference/model/llm/transformers/opt.py +3 -7
  84. xinference/model/llm/utils.py +34 -49
  85. xinference/model/llm/vllm/core.py +77 -27
  86. xinference/model/llm/vllm/xavier/engine.py +5 -3
  87. xinference/model/llm/vllm/xavier/scheduler.py +10 -6
  88. xinference/model/llm/vllm/xavier/transfer.py +1 -1
  89. xinference/model/rerank/__init__.py +26 -25
  90. xinference/model/rerank/core.py +47 -87
  91. xinference/model/rerank/custom.py +25 -71
  92. xinference/model/rerank/model_spec.json +158 -33
  93. xinference/model/rerank/utils.py +2 -2
  94. xinference/model/utils.py +115 -54
  95. xinference/model/video/__init__.py +13 -17
  96. xinference/model/video/core.py +44 -102
  97. xinference/model/video/diffusers.py +4 -3
  98. xinference/model/video/model_spec.json +90 -21
  99. xinference/types.py +5 -3
  100. xinference/web/ui/build/asset-manifest.json +3 -3
  101. xinference/web/ui/build/index.html +1 -1
  102. xinference/web/ui/build/static/js/main.7d24df53.js +3 -0
  103. xinference/web/ui/build/static/js/main.7d24df53.js.map +1 -0
  104. xinference/web/ui/node_modules/.cache/babel-loader/2704ff66a5f73ca78b341eb3edec60154369df9d87fbc8c6dd60121abc5e1b0a.json +1 -0
  105. xinference/web/ui/node_modules/.cache/babel-loader/607dfef23d33e6b594518c0c6434567639f24f356b877c80c60575184ec50ed0.json +1 -0
  106. xinference/web/ui/node_modules/.cache/babel-loader/9be3d56173aacc3efd0b497bcb13c4f6365de30069176ee9403b40e717542326.json +1 -0
  107. xinference/web/ui/node_modules/.cache/babel-loader/9f9dd6c32c78a222d07da5987ae902effe16bcf20aac00774acdccc4de3c9ff2.json +1 -0
  108. xinference/web/ui/node_modules/.cache/babel-loader/b2ab5ee972c60d15eb9abf5845705f8ab7e1d125d324d9a9b1bcae5d6fd7ffb2.json +1 -0
  109. xinference/web/ui/src/locales/en.json +0 -1
  110. xinference/web/ui/src/locales/ja.json +0 -1
  111. xinference/web/ui/src/locales/ko.json +0 -1
  112. xinference/web/ui/src/locales/zh.json +0 -1
  113. {xinference-1.7.1.dist-info → xinference-1.8.0.dist-info}/METADATA +9 -11
  114. {xinference-1.7.1.dist-info → xinference-1.8.0.dist-info}/RECORD +119 -119
  115. xinference/model/audio/model_spec_modelscope.json +0 -231
  116. xinference/model/embedding/model_spec_modelscope.json +0 -293
  117. xinference/model/embedding/utils.py +0 -18
  118. xinference/model/image/model_spec_modelscope.json +0 -375
  119. xinference/model/llm/llama_cpp/memory.py +0 -457
  120. xinference/model/llm/llm_family_csghub.json +0 -56
  121. xinference/model/llm/llm_family_modelscope.json +0 -8700
  122. xinference/model/llm/llm_family_openmind_hub.json +0 -1019
  123. xinference/model/rerank/model_spec_modelscope.json +0 -85
  124. xinference/model/video/model_spec_modelscope.json +0 -184
  125. xinference/web/ui/build/static/js/main.9b12b7f9.js +0 -3
  126. xinference/web/ui/build/static/js/main.9b12b7f9.js.map +0 -1
  127. xinference/web/ui/node_modules/.cache/babel-loader/1460361af6975e63576708039f1cb732faf9c672d97c494d4055fc6331460be0.json +0 -1
  128. xinference/web/ui/node_modules/.cache/babel-loader/4efd8dda58fda83ed9546bf2f587df67f8d98e639117bee2d9326a9a1d9bebb2.json +0 -1
  129. xinference/web/ui/node_modules/.cache/babel-loader/55b9fb40b57fa926e8f05f31c2f96467e76e5ad62f033dca97c03f9e8c4eb4fe.json +0 -1
  130. xinference/web/ui/node_modules/.cache/babel-loader/5b2dafe5aa9e1105e0244a2b6751807342fa86aa0144b4e84d947a1686102715.json +0 -1
  131. xinference/web/ui/node_modules/.cache/babel-loader/611fa2c6c53b66039991d06dfb0473b5ab37fc63b4564e0f6e1718523768a045.json +0 -1
  132. /xinference/web/ui/build/static/js/{main.9b12b7f9.js.LICENSE.txt → main.7d24df53.js.LICENSE.txt} +0 -0
  133. {xinference-1.7.1.dist-info → xinference-1.8.0.dist-info}/WHEEL +0 -0
  134. {xinference-1.7.1.dist-info → xinference-1.8.0.dist-info}/entry_points.txt +0 -0
  135. {xinference-1.7.1.dist-info → xinference-1.8.0.dist-info}/licenses/LICENSE +0 -0
  136. {xinference-1.7.1.dist-info → xinference-1.8.0.dist-info}/top_level.txt +0 -0
@@ -1,194 +1,368 @@
1
1
  [
2
2
  {
3
+ "version": 2,
3
4
  "model_name": "whisper-tiny",
4
5
  "model_family": "whisper",
5
- "model_id": "openai/whisper-tiny",
6
- "model_revision": "167c219b21f11ef214220b8fdb7536b8a88c2475",
7
- "model_ability": ["audio2text"],
8
- "multilingual": true
6
+ "model_ability": [
7
+ "audio2text"
8
+ ],
9
+ "multilingual": true,
10
+ "model_src": {
11
+ "huggingface": {
12
+ "model_id": "openai/whisper-tiny",
13
+ "model_revision": "167c219b21f11ef214220b8fdb7536b8a88c2475"
14
+ }
15
+ }
9
16
  },
10
17
  {
18
+ "version": 2,
11
19
  "model_name": "whisper-tiny.en",
12
20
  "model_family": "whisper",
13
- "model_id": "openai/whisper-tiny.en",
14
- "model_revision": "87c7102498dcde7456f24cfd30239ca606ed9063",
15
- "model_ability": ["audio2text"],
16
- "multilingual": false
21
+ "model_ability": [
22
+ "audio2text"
23
+ ],
24
+ "multilingual": false,
25
+ "model_src": {
26
+ "huggingface": {
27
+ "model_id": "openai/whisper-tiny.en",
28
+ "model_revision": "87c7102498dcde7456f24cfd30239ca606ed9063"
29
+ }
30
+ }
17
31
  },
18
32
  {
33
+ "version": 2,
19
34
  "model_name": "whisper-base",
20
35
  "model_family": "whisper",
21
- "model_id": "openai/whisper-base",
22
- "model_revision": "8c1db9b51951100007a96a525d83a8ec81b3c237",
23
- "model_ability": ["audio2text"],
24
- "multilingual": true
36
+ "model_ability": [
37
+ "audio2text"
38
+ ],
39
+ "multilingual": true,
40
+ "model_src": {
41
+ "huggingface": {
42
+ "model_id": "openai/whisper-base",
43
+ "model_revision": "8c1db9b51951100007a96a525d83a8ec81b3c237"
44
+ }
45
+ }
25
46
  },
26
47
  {
48
+ "version": 2,
27
49
  "model_name": "whisper-base.en",
28
50
  "model_family": "whisper",
29
- "model_id": "openai/whisper-base.en",
30
- "model_revision": "911407f4214e0e1d82085af863093ec0b66f9cd6",
31
- "model_ability": ["audio2text"],
32
- "multilingual": false
51
+ "model_ability": [
52
+ "audio2text"
53
+ ],
54
+ "multilingual": false,
55
+ "model_src": {
56
+ "huggingface": {
57
+ "model_id": "openai/whisper-base.en",
58
+ "model_revision": "911407f4214e0e1d82085af863093ec0b66f9cd6"
59
+ }
60
+ }
33
61
  },
34
62
  {
63
+ "version": 2,
35
64
  "model_name": "whisper-small",
36
65
  "model_family": "whisper",
37
- "model_id": "openai/whisper-small",
38
- "model_revision": "998cb1a777c20db53d6033a61b977ed4c3792cac",
39
- "model_ability": ["audio2text"],
40
- "multilingual": true
66
+ "model_ability": [
67
+ "audio2text"
68
+ ],
69
+ "multilingual": true,
70
+ "model_src": {
71
+ "huggingface": {
72
+ "model_id": "openai/whisper-small",
73
+ "model_revision": "998cb1a777c20db53d6033a61b977ed4c3792cac"
74
+ }
75
+ }
41
76
  },
42
77
  {
78
+ "version": 2,
43
79
  "model_name": "whisper-small.en",
44
80
  "model_family": "whisper",
45
- "model_id": "openai/whisper-small.en",
46
- "model_revision": "e8727524f962ee844a7319d92be39ac1bd25655a",
47
- "model_ability": ["audio2text"],
48
- "multilingual": false
81
+ "model_ability": [
82
+ "audio2text"
83
+ ],
84
+ "multilingual": false,
85
+ "model_src": {
86
+ "huggingface": {
87
+ "model_id": "openai/whisper-small.en",
88
+ "model_revision": "e8727524f962ee844a7319d92be39ac1bd25655a"
89
+ }
90
+ }
49
91
  },
50
92
  {
93
+ "version": 2,
51
94
  "model_name": "whisper-medium",
52
95
  "model_family": "whisper",
53
- "model_id": "openai/whisper-medium",
54
- "model_revision": "16688beb1294bedd0a6f5cd86fe7eec57bce41ed",
55
- "model_ability": ["audio2text"],
56
- "multilingual": true
96
+ "model_ability": [
97
+ "audio2text"
98
+ ],
99
+ "multilingual": true,
100
+ "model_src": {
101
+ "huggingface": {
102
+ "model_id": "openai/whisper-medium",
103
+ "model_revision": "16688beb1294bedd0a6f5cd86fe7eec57bce41ed"
104
+ }
105
+ }
57
106
  },
58
107
  {
108
+ "version": 2,
59
109
  "model_name": "whisper-medium.en",
60
110
  "model_family": "whisper",
61
- "model_id": "openai/whisper-medium.en",
62
- "model_revision": "2e98eb6279edf5095af0c8dedb36bdec0acd172b",
63
- "model_ability": ["audio2text"],
64
- "multilingual": false
111
+ "model_ability": [
112
+ "audio2text"
113
+ ],
114
+ "multilingual": false,
115
+ "model_src": {
116
+ "huggingface": {
117
+ "model_id": "openai/whisper-medium.en",
118
+ "model_revision": "2e98eb6279edf5095af0c8dedb36bdec0acd172b"
119
+ }
120
+ }
65
121
  },
66
122
  {
123
+ "version": 2,
67
124
  "model_name": "whisper-large-v3",
68
125
  "model_family": "whisper",
69
- "model_id": "openai/whisper-large-v3",
70
- "model_revision": "6cdf07a7e3ec3806e5d55f787915b85d4cd020b1",
71
- "model_ability": ["audio2text"],
72
- "multilingual": true
126
+ "model_ability": [
127
+ "audio2text"
128
+ ],
129
+ "multilingual": true,
130
+ "model_src": {
131
+ "huggingface": {
132
+ "model_id": "openai/whisper-large-v3",
133
+ "model_revision": "6cdf07a7e3ec3806e5d55f787915b85d4cd020b1"
134
+ },
135
+ "modelscope": {
136
+ "model_id": "AI-ModelScope/whisper-large-v3",
137
+ "model_revision": "master"
138
+ }
139
+ }
73
140
  },
74
141
  {
142
+ "version": 2,
75
143
  "model_name": "whisper-large-v3-turbo",
76
144
  "model_family": "whisper",
77
- "model_id": "openai/whisper-large-v3-turbo",
78
- "model_revision": "41f01f3fe87f28c78e2fbf8b568835947dd65ed9",
79
- "model_ability": ["audio2text"],
80
- "multilingual": true
145
+ "model_ability": [
146
+ "audio2text"
147
+ ],
148
+ "multilingual": true,
149
+ "model_src": {
150
+ "huggingface": {
151
+ "model_id": "openai/whisper-large-v3-turbo",
152
+ "model_revision": "41f01f3fe87f28c78e2fbf8b568835947dd65ed9"
153
+ },
154
+ "modelscope": {
155
+ "model_id": "AI-ModelScope/whisper-large-v3-turbo",
156
+ "model_revision": "master"
157
+ }
158
+ }
81
159
  },
82
160
  {
161
+ "version": 2,
83
162
  "model_name": "Belle-distilwhisper-large-v2-zh",
84
163
  "model_family": "whisper",
85
- "model_id": "BELLE-2/Belle-distilwhisper-large-v2-zh",
86
- "model_revision": "ed25d13498fa5bac758b2fc479435b698532dfe8",
87
- "model_ability": ["audio2text"],
88
- "multilingual": false
164
+ "model_ability": [
165
+ "audio2text"
166
+ ],
167
+ "multilingual": false,
168
+ "model_src": {
169
+ "huggingface": {
170
+ "model_id": "BELLE-2/Belle-distilwhisper-large-v2-zh",
171
+ "model_revision": "ed25d13498fa5bac758b2fc479435b698532dfe8"
172
+ }
173
+ }
89
174
  },
90
175
  {
176
+ "version": 2,
91
177
  "model_name": "Belle-whisper-large-v2-zh",
92
178
  "model_family": "whisper",
93
- "model_id": "BELLE-2/Belle-whisper-large-v2-zh",
94
- "model_revision": "ec5bd5d78598545b7585814edde86dac2002b5b9",
95
- "model_ability": ["audio2text"],
96
- "multilingual": false
179
+ "model_ability": [
180
+ "audio2text"
181
+ ],
182
+ "multilingual": false,
183
+ "model_src": {
184
+ "huggingface": {
185
+ "model_id": "BELLE-2/Belle-whisper-large-v2-zh",
186
+ "model_revision": "ec5bd5d78598545b7585814edde86dac2002b5b9"
187
+ }
188
+ }
97
189
  },
98
190
  {
191
+ "version": 2,
99
192
  "model_name": "Belle-whisper-large-v3-zh",
100
193
  "model_family": "whisper",
101
- "model_id": "BELLE-2/Belle-whisper-large-v3-zh",
102
- "model_revision": "3bebc7247696b39f5ab9ed22db426943ac33f600",
103
- "model_ability": ["audio2text"],
104
- "multilingual": false
194
+ "model_ability": [
195
+ "audio2text"
196
+ ],
197
+ "multilingual": false,
198
+ "model_src": {
199
+ "huggingface": {
200
+ "model_id": "BELLE-2/Belle-whisper-large-v3-zh",
201
+ "model_revision": "3bebc7247696b39f5ab9ed22db426943ac33f600"
202
+ },
203
+ "modelscope": {
204
+ "model_id": "Xorbits/Belle-whisper-large-v3-zh",
205
+ "model_revision": "master"
206
+ }
207
+ }
105
208
  },
106
209
  {
210
+ "version": 2,
107
211
  "model_name": "whisper-tiny-mlx",
108
212
  "model_family": "whisper",
109
- "model_id": "mlx-community/whisper-tiny",
110
- "model_ability": ["audio2text"],
213
+ "model_ability": [
214
+ "audio2text"
215
+ ],
111
216
  "multilingual": true,
112
- "engine": "mlx"
217
+ "engine": "mlx",
218
+ "model_src": {
219
+ "huggingface": {
220
+ "model_id": "mlx-community/whisper-tiny"
221
+ }
222
+ }
113
223
  },
114
224
  {
225
+ "version": 2,
115
226
  "model_name": "whisper-tiny.en-mlx",
116
227
  "model_family": "whisper",
117
- "model_id": "mlx-community/whisper-tiny.en-mlx",
118
- "model_ability": ["audio2text"],
228
+ "model_ability": [
229
+ "audio2text"
230
+ ],
119
231
  "multilingual": false,
120
- "engine": "mlx"
232
+ "engine": "mlx",
233
+ "model_src": {
234
+ "huggingface": {
235
+ "model_id": "mlx-community/whisper-tiny.en-mlx"
236
+ }
237
+ }
121
238
  },
122
239
  {
240
+ "version": 2,
123
241
  "model_name": "whisper-base-mlx",
124
242
  "model_family": "whisper",
125
- "model_id": "mlx-community/whisper-base-mlx",
126
- "model_ability": ["audio2text"],
243
+ "model_ability": [
244
+ "audio2text"
245
+ ],
127
246
  "multilingual": true,
128
- "engine": "mlx"
247
+ "engine": "mlx",
248
+ "model_src": {
249
+ "huggingface": {
250
+ "model_id": "mlx-community/whisper-base-mlx"
251
+ }
252
+ }
129
253
  },
130
254
  {
255
+ "version": 2,
131
256
  "model_name": "whisper-base.en-mlx",
132
257
  "model_family": "whisper",
133
- "model_id": "mlx-community/whisper-base.en-mlx",
134
- "model_ability": ["audio2text"],
258
+ "model_ability": [
259
+ "audio2text"
260
+ ],
135
261
  "multilingual": false,
136
- "engine": "mlx"
262
+ "engine": "mlx",
263
+ "model_src": {
264
+ "huggingface": {
265
+ "model_id": "mlx-community/whisper-base.en-mlx"
266
+ }
267
+ }
137
268
  },
138
269
  {
270
+ "version": 2,
139
271
  "model_name": "whisper-small-mlx",
140
272
  "model_family": "whisper",
141
- "model_id": "mlx-community/whisper-small-mlx",
142
- "model_ability": ["audio2text"],
273
+ "model_ability": [
274
+ "audio2text"
275
+ ],
143
276
  "multilingual": true,
144
- "engine": "mlx"
277
+ "engine": "mlx",
278
+ "model_src": {
279
+ "huggingface": {
280
+ "model_id": "mlx-community/whisper-small-mlx"
281
+ }
282
+ }
145
283
  },
146
284
  {
285
+ "version": 2,
147
286
  "model_name": "whisper-small.en-mlx",
148
287
  "model_family": "whisper",
149
- "model_id": "mlx-community/whisper-small.en-mlx",
150
- "model_ability": ["audio2text"],
288
+ "model_ability": [
289
+ "audio2text"
290
+ ],
151
291
  "multilingual": false,
152
- "engine": "mlx"
292
+ "engine": "mlx",
293
+ "model_src": {
294
+ "huggingface": {
295
+ "model_id": "mlx-community/whisper-small.en-mlx"
296
+ }
297
+ }
153
298
  },
154
299
  {
300
+ "version": 2,
155
301
  "model_name": "whisper-medium-mlx",
156
302
  "model_family": "whisper",
157
- "model_id": "mlx-community/whisper-medium-mlx",
158
- "model_ability": ["audio2text"],
303
+ "model_ability": [
304
+ "audio2text"
305
+ ],
159
306
  "multilingual": true,
160
- "engine": "mlx"
307
+ "engine": "mlx",
308
+ "model_src": {
309
+ "huggingface": {
310
+ "model_id": "mlx-community/whisper-medium-mlx"
311
+ }
312
+ }
161
313
  },
162
314
  {
315
+ "version": 2,
163
316
  "model_name": "whisper-medium.en-mlx",
164
317
  "model_family": "whisper",
165
- "model_id": "mlx-community/whisper-medium.en-mlx",
166
- "model_ability": ["audio2text"],
318
+ "model_ability": [
319
+ "audio2text"
320
+ ],
167
321
  "multilingual": false,
168
- "engine": "mlx"
322
+ "engine": "mlx",
323
+ "model_src": {
324
+ "huggingface": {
325
+ "model_id": "mlx-community/whisper-medium.en-mlx"
326
+ }
327
+ }
169
328
  },
170
329
  {
330
+ "version": 2,
171
331
  "model_name": "whisper-large-v3-mlx",
172
332
  "model_family": "whisper",
173
- "model_id": "mlx-community/whisper-large-v3-mlx",
174
- "model_ability": ["audio2text"],
333
+ "model_ability": [
334
+ "audio2text"
335
+ ],
175
336
  "multilingual": true,
176
- "engine": "mlx"
337
+ "engine": "mlx",
338
+ "model_src": {
339
+ "huggingface": {
340
+ "model_id": "mlx-community/whisper-large-v3-mlx"
341
+ }
342
+ }
177
343
  },
178
344
  {
345
+ "version": 2,
179
346
  "model_name": "whisper-large-v3-turbo-mlx",
180
347
  "model_family": "whisper",
181
- "model_id": "mlx-community/whisper-large-v3-turbo",
182
- "model_ability": ["audio2text"],
348
+ "model_ability": [
349
+ "audio2text"
350
+ ],
183
351
  "multilingual": true,
184
- "engine": "mlx"
352
+ "engine": "mlx",
353
+ "model_src": {
354
+ "huggingface": {
355
+ "model_id": "mlx-community/whisper-large-v3-turbo"
356
+ }
357
+ }
185
358
  },
186
359
  {
360
+ "version": 2,
187
361
  "model_name": "SenseVoiceSmall",
188
362
  "model_family": "funasr",
189
- "model_id": "FunAudioLLM/SenseVoiceSmall",
190
- "model_revision": "3eb3b4eeffc2f2dde6051b853983753db33e35c3",
191
- "model_ability": ["audio2text"],
363
+ "model_ability": [
364
+ "audio2text"
365
+ ],
192
366
  "multilingual": true,
193
367
  "default_model_config": {
194
368
  "vad_model": "fsmn-vad",
@@ -201,14 +375,25 @@
201
375
  "batch_size_s": 60,
202
376
  "merge_vad": true,
203
377
  "merge_length_s": 15
378
+ },
379
+ "model_src": {
380
+ "huggingface": {
381
+ "model_id": "FunAudioLLM/SenseVoiceSmall",
382
+ "model_revision": "3eb3b4eeffc2f2dde6051b853983753db33e35c3"
383
+ },
384
+ "modelscope": {
385
+ "model_id": "iic/SenseVoiceSmall",
386
+ "model_revision": "master"
387
+ }
204
388
  }
205
389
  },
206
390
  {
391
+ "version": 2,
207
392
  "model_name": "paraformer-zh",
208
393
  "model_family": "funasr",
209
- "model_id": "funasr/paraformer-zh",
210
- "model_revision": "5ed094cdfc8f6a9b6b022bd08bc904ef862bc79e",
211
- "model_ability": ["audio2text"],
394
+ "model_ability": [
395
+ "audio2text"
396
+ ],
212
397
  "multilingual": false,
213
398
  "default_model_config": {
214
399
  "vad_model": "fsmn-vad",
@@ -216,14 +401,25 @@
216
401
  },
217
402
  "default_transcription_config": {
218
403
  "batch_size_s": 300
404
+ },
405
+ "model_src": {
406
+ "huggingface": {
407
+ "model_id": "funasr/paraformer-zh",
408
+ "model_revision": "5ed094cdfc8f6a9b6b022bd08bc904ef862bc79e"
409
+ },
410
+ "modelscope": {
411
+ "model_id": "iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
412
+ "model_revision": "master"
413
+ }
219
414
  }
220
415
  },
221
416
  {
417
+ "version": 2,
222
418
  "model_name": "paraformer-zh-hotword",
223
419
  "model_family": "funasr",
224
- "model_id": "JunHowie/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
225
- "model_revision": "26d622993683d7b0c517ee5ec9c1c8bdde76e324",
226
- "model_ability": ["audio2text"],
420
+ "model_ability": [
421
+ "audio2text"
422
+ ],
227
423
  "multilingual": false,
228
424
  "default_model_config": {
229
425
  "vad_model": "fsmn-vad",
@@ -232,14 +428,25 @@
232
428
  "default_transcription_config": {
233
429
  "hotword": "",
234
430
  "batch_size_s": 300
431
+ },
432
+ "model_src": {
433
+ "huggingface": {
434
+ "model_id": "JunHowie/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
435
+ "model_revision": "26d622993683d7b0c517ee5ec9c1c8bdde76e324"
436
+ },
437
+ "modelscope": {
438
+ "model_id": "iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
439
+ "model_revision": "master"
440
+ }
235
441
  }
236
442
  },
237
443
  {
444
+ "version": 2,
238
445
  "model_name": "paraformer-zh-long",
239
446
  "model_family": "funasr",
240
- "model_id": "JunHowie/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
241
- "model_revision": "b6d8cb81645e34056cd3dda41e5624a740587de3",
242
- "model_ability": ["audio2text"],
447
+ "model_ability": [
448
+ "audio2text"
449
+ ],
243
450
  "multilingual": false,
244
451
  "default_model_config": {
245
452
  "vad_model": "fsmn-vad",
@@ -247,30 +454,52 @@
247
454
  },
248
455
  "default_transcription_config": {
249
456
  "batch_size_s": 300
457
+ },
458
+ "model_src": {
459
+ "huggingface": {
460
+ "model_id": "JunHowie/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
461
+ "model_revision": "b6d8cb81645e34056cd3dda41e5624a740587de3"
462
+ },
463
+ "modelscope": {
464
+ "model_id": "iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
465
+ "model_revision": "master"
466
+ }
250
467
  }
251
468
  },
252
469
  {
470
+ "version": 2,
253
471
  "model_name": "paraformer-zh-spk",
254
472
  "model_family": "funasr",
255
- "model_id": "JunHowie/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn",
256
- "model_revision": "36abd64af4392fe02bf76453bc86c081cf1ca6da",
257
- "model_ability": ["audio2text"],
473
+ "model_ability": [
474
+ "audio2text"
475
+ ],
258
476
  "multilingual": false,
259
477
  "default_model_config": {
260
478
  "vad_model": "fsmn-vad",
261
479
  "punc_model": "ct-punc",
262
- "spk_model":"cam++"
480
+ "spk_model": "cam++"
263
481
  },
264
482
  "default_transcription_config": {
265
483
  "batch_size_s": 300
484
+ },
485
+ "model_src": {
486
+ "huggingface": {
487
+ "model_id": "JunHowie/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn",
488
+ "model_revision": "36abd64af4392fe02bf76453bc86c081cf1ca6da"
489
+ },
490
+ "modelscope": {
491
+ "model_id": "iic/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn",
492
+ "model_revision": "master"
493
+ }
266
494
  }
267
495
  },
268
496
  {
497
+ "version": 2,
269
498
  "model_name": "seaco-paraformer-zh",
270
499
  "model_family": "funasr",
271
- "model_id": "JunHowie/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
272
- "model_revision": "42e6be00854cf8de0f40002794f99df2a444fa97",
273
- "model_ability": ["audio2text"],
500
+ "model_ability": [
501
+ "audio2text"
502
+ ],
274
503
  "multilingual": false,
275
504
  "default_model_config": {
276
505
  "vad_model": "fsmn-vad",
@@ -279,14 +508,25 @@
279
508
  "default_transcription_config": {
280
509
  "hotword": "",
281
510
  "batch_size_s": 300
511
+ },
512
+ "model_src": {
513
+ "huggingface": {
514
+ "model_id": "JunHowie/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
515
+ "model_revision": "42e6be00854cf8de0f40002794f99df2a444fa97"
516
+ },
517
+ "modelscope": {
518
+ "model_id": "iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
519
+ "model_revision": "master"
520
+ }
282
521
  }
283
522
  },
284
523
  {
524
+ "version": 2,
285
525
  "model_name": "ChatTTS",
286
526
  "model_family": "ChatTTS",
287
- "model_id": "2Noise/ChatTTS",
288
- "model_revision": "1a3c04a8b0651689bd9242fbb55b1f4b5a9aef84",
289
- "model_ability": ["text2audio"],
527
+ "model_ability": [
528
+ "text2audio"
529
+ ],
290
530
  "multilingual": true,
291
531
  "virtualenv": {
292
532
  "packages": [
@@ -294,38 +534,82 @@
294
534
  "#system_torch#",
295
535
  "#system_numpy#"
296
536
  ]
537
+ },
538
+ "model_src": {
539
+ "huggingface": {
540
+ "model_id": "2Noise/ChatTTS",
541
+ "model_revision": "1a3c04a8b0651689bd9242fbb55b1f4b5a9aef84"
542
+ },
543
+ "modelscope": {
544
+ "model_id": "AI-ModelScope/ChatTTS",
545
+ "model_revision": "master"
546
+ }
297
547
  }
298
548
  },
299
549
  {
550
+ "version": 2,
300
551
  "model_name": "CosyVoice-300M",
301
552
  "model_family": "CosyVoice",
302
- "model_id": "FunAudioLLM/CosyVoice-300M",
303
- "model_revision": "39c4e13d46bd4dfb840d214547623e5fcd2428e2",
304
- "model_ability": ["text2audio"],
305
- "multilingual": true
553
+ "model_ability": [
554
+ "text2audio"
555
+ ],
556
+ "multilingual": true,
557
+ "model_src": {
558
+ "huggingface": {
559
+ "model_id": "FunAudioLLM/CosyVoice-300M",
560
+ "model_revision": "39c4e13d46bd4dfb840d214547623e5fcd2428e2"
561
+ },
562
+ "modelscope": {
563
+ "model_id": "iic/CosyVoice-300M",
564
+ "model_revision": "master"
565
+ }
566
+ }
306
567
  },
307
568
  {
569
+ "version": 2,
308
570
  "model_name": "CosyVoice-300M-SFT",
309
571
  "model_family": "CosyVoice",
310
- "model_id": "FunAudioLLM/CosyVoice-300M-SFT",
311
- "model_revision": "096a5cff8d497fabb3dec2756a200f3688457a1b",
312
- "model_ability": ["text2audio"],
313
- "multilingual": true
572
+ "model_ability": [
573
+ "text2audio"
574
+ ],
575
+ "multilingual": true,
576
+ "model_src": {
577
+ "huggingface": {
578
+ "model_id": "FunAudioLLM/CosyVoice-300M-SFT",
579
+ "model_revision": "096a5cff8d497fabb3dec2756a200f3688457a1b"
580
+ },
581
+ "modelscope": {
582
+ "model_id": "iic/CosyVoice-300M-SFT",
583
+ "model_revision": "master"
584
+ }
585
+ }
314
586
  },
315
587
  {
588
+ "version": 2,
316
589
  "model_name": "CosyVoice-300M-Instruct",
317
590
  "model_family": "CosyVoice",
318
- "model_id": "FunAudioLLM/CosyVoice-300M-Instruct",
319
- "model_revision": "ba5265d9a3169c1fedce145122c9dd4bc24e062c",
320
- "model_ability": ["text2audio"],
321
- "multilingual": true
591
+ "model_ability": [
592
+ "text2audio"
593
+ ],
594
+ "multilingual": true,
595
+ "model_src": {
596
+ "huggingface": {
597
+ "model_id": "FunAudioLLM/CosyVoice-300M-Instruct",
598
+ "model_revision": "ba5265d9a3169c1fedce145122c9dd4bc24e062c"
599
+ },
600
+ "modelscope": {
601
+ "model_id": "iic/CosyVoice-300M-Instruct",
602
+ "model_revision": "master"
603
+ }
604
+ }
322
605
  },
323
606
  {
607
+ "version": 2,
324
608
  "model_name": "CosyVoice2-0.5B",
325
609
  "model_family": "CosyVoice",
326
- "model_id": "JunHowie/CosyVoice2-0.5B",
327
- "model_revision": "7ac9e9a026aec35efe48cde1196eaad6a00ad5f2",
328
- "model_ability": ["text2audio"],
610
+ "model_ability": [
611
+ "text2audio"
612
+ ],
329
613
  "multilingual": true,
330
614
  "virtualenv": {
331
615
  "packages": [
@@ -345,118 +629,235 @@
345
629
  "#system_numpy#",
346
630
  "#system_torch#"
347
631
  ]
632
+ },
633
+ "model_src": {
634
+ "huggingface": {
635
+ "model_id": "JunHowie/CosyVoice2-0.5B",
636
+ "model_revision": "7ac9e9a026aec35efe48cde1196eaad6a00ad5f2"
637
+ },
638
+ "modelscope": {
639
+ "model_id": "iic/CosyVoice2-0.5B",
640
+ "model_revision": "master"
641
+ }
348
642
  }
349
643
  },
350
644
  {
645
+ "version": 2,
351
646
  "model_name": "FishSpeech-1.5",
352
647
  "model_family": "FishAudio",
353
- "model_id": "fishaudio/fish-speech-1.5",
354
- "model_revision": "268b6ec86243dd683bc78dab7e9a6cedf9191f2a",
355
- "model_ability": ["text2audio"],
356
- "multilingual": true
648
+ "model_ability": [
649
+ "text2audio"
650
+ ],
651
+ "multilingual": true,
652
+ "model_src": {
653
+ "huggingface": {
654
+ "model_id": "fishaudio/fish-speech-1.5",
655
+ "model_revision": "268b6ec86243dd683bc78dab7e9a6cedf9191f2a"
656
+ },
657
+ "modelscope": {
658
+ "model_id": "fishaudio/fish-speech-1.5",
659
+ "model_revision": "master"
660
+ }
661
+ }
357
662
  },
358
663
  {
664
+ "version": 2,
359
665
  "model_name": "F5-TTS",
360
666
  "model_family": "F5-TTS",
361
- "model_id": "SWivid/F5-TTS",
362
- "model_revision": "4dcc16f297f2ff98a17b3726b16f5de5a5e45672",
363
- "model_ability": ["text2audio"],
364
- "multilingual": true
667
+ "model_ability": [
668
+ "text2audio"
669
+ ],
670
+ "multilingual": true,
671
+ "model_src": {
672
+ "huggingface": {
673
+ "model_id": "SWivid/F5-TTS",
674
+ "model_revision": "4dcc16f297f2ff98a17b3726b16f5de5a5e45672"
675
+ },
676
+ "modelscope": {
677
+ "model_id": "SWivid/F5-TTS_Emilia-ZH-EN",
678
+ "model_revision": "master"
679
+ }
680
+ }
365
681
  },
366
682
  {
683
+ "version": 2,
367
684
  "model_name": "F5-TTS-MLX",
368
685
  "model_family": "F5-TTS-MLX",
369
- "model_id": "lucasnewman/f5-tts-mlx",
370
- "model_revision": "7642bb232e3fcacf92c51c786edebb8624da6b93",
371
- "model_ability": ["text2audio"],
372
- "multilingual": true
686
+ "model_ability": [
687
+ "text2audio"
688
+ ],
689
+ "multilingual": true,
690
+ "model_src": {
691
+ "huggingface": {
692
+ "model_id": "lucasnewman/f5-tts-mlx",
693
+ "model_revision": "7642bb232e3fcacf92c51c786edebb8624da6b93"
694
+ }
695
+ }
373
696
  },
374
697
  {
698
+ "version": 2,
375
699
  "model_name": "MeloTTS-English",
376
700
  "model_family": "MeloTTS",
377
- "model_id": "myshell-ai/MeloTTS-English",
378
- "model_revision": "bb4fb7346d566d277ba8c8c7dbfdf6786139b8ef",
379
- "model_ability": ["text2audio"],
701
+ "model_ability": [
702
+ "text2audio"
703
+ ],
380
704
  "multilingual": false,
381
- "language": "EN"
705
+ "language": "EN",
706
+ "model_src": {
707
+ "huggingface": {
708
+ "model_id": "myshell-ai/MeloTTS-English",
709
+ "model_revision": "bb4fb7346d566d277ba8c8c7dbfdf6786139b8ef"
710
+ }
711
+ }
382
712
  },
383
713
  {
714
+ "version": 2,
384
715
  "model_name": "MeloTTS-English-v2",
385
716
  "model_family": "MeloTTS",
386
- "model_id": "myshell-ai/MeloTTS-English-v2",
387
- "model_revision": "a53e3509c4ee4ff16d79272feb2474ff864e18f3",
388
- "model_ability": ["text2audio"],
717
+ "model_ability": [
718
+ "text2audio"
719
+ ],
389
720
  "multilingual": false,
390
- "language": "EN"
721
+ "language": "EN",
722
+ "model_src": {
723
+ "huggingface": {
724
+ "model_id": "myshell-ai/MeloTTS-English-v2",
725
+ "model_revision": "a53e3509c4ee4ff16d79272feb2474ff864e18f3"
726
+ }
727
+ }
391
728
  },
392
729
  {
730
+ "version": 2,
393
731
  "model_name": "MeloTTS-English-v3",
394
732
  "model_family": "MeloTTS",
395
- "model_id": "myshell-ai/MeloTTS-English-v3",
396
- "model_revision": "f7c4a35392c0e9be24a755f1edb4c3f63040f759",
397
- "model_ability": ["text2audio"],
733
+ "model_ability": [
734
+ "text2audio"
735
+ ],
398
736
  "multilingual": false,
399
- "language": "EN"
737
+ "language": "EN",
738
+ "model_src": {
739
+ "huggingface": {
740
+ "model_id": "myshell-ai/MeloTTS-English-v3",
741
+ "model_revision": "f7c4a35392c0e9be24a755f1edb4c3f63040f759"
742
+ }
743
+ }
400
744
  },
401
745
  {
746
+ "version": 2,
402
747
  "model_name": "MeloTTS-French",
403
748
  "model_family": "MeloTTS",
404
- "model_id": "myshell-ai/MeloTTS-French",
405
- "model_revision": "1e9bf590262392d8bffb679b0a3b0c16b0f9fdaf",
406
- "model_ability": ["text2audio"],
749
+ "model_ability": [
750
+ "text2audio"
751
+ ],
407
752
  "multilingual": false,
408
- "language": "FR"
753
+ "language": "FR",
754
+ "model_src": {
755
+ "huggingface": {
756
+ "model_id": "myshell-ai/MeloTTS-French",
757
+ "model_revision": "1e9bf590262392d8bffb679b0a3b0c16b0f9fdaf"
758
+ }
759
+ }
409
760
  },
410
761
  {
762
+ "version": 2,
411
763
  "model_name": "MeloTTS-Japanese",
412
764
  "model_family": "MeloTTS",
413
- "model_id": "myshell-ai/MeloTTS-Japanese",
414
- "model_revision": "367f8795464b531b4e97c1515bddfc1243e60891",
415
- "model_ability": ["text2audio"],
765
+ "model_ability": [
766
+ "text2audio"
767
+ ],
416
768
  "multilingual": false,
417
- "language": "JP"
769
+ "language": "JP",
770
+ "model_src": {
771
+ "huggingface": {
772
+ "model_id": "myshell-ai/MeloTTS-Japanese",
773
+ "model_revision": "367f8795464b531b4e97c1515bddfc1243e60891"
774
+ }
775
+ }
418
776
  },
419
777
  {
778
+ "version": 2,
420
779
  "model_name": "MeloTTS-Spanish",
421
780
  "model_family": "MeloTTS",
422
- "model_id": "myshell-ai/MeloTTS-Spanish",
423
- "model_revision": "dbb5496df39d11a66c1d5f5a9ca357c3c9fb95fb",
424
- "model_ability": ["text2audio"],
781
+ "model_ability": [
782
+ "text2audio"
783
+ ],
425
784
  "multilingual": false,
426
- "language": "ES"
785
+ "language": "ES",
786
+ "model_src": {
787
+ "huggingface": {
788
+ "model_id": "myshell-ai/MeloTTS-Spanish",
789
+ "model_revision": "dbb5496df39d11a66c1d5f5a9ca357c3c9fb95fb"
790
+ }
791
+ }
427
792
  },
428
793
  {
794
+ "version": 2,
429
795
  "model_name": "MeloTTS-Chinese",
430
796
  "model_family": "MeloTTS",
431
- "model_id": "myshell-ai/MeloTTS-Chinese",
432
- "model_revision": "af5d207a364ea4208c6f589c89f57f88414bdd16",
433
- "model_ability": ["text2audio"],
797
+ "model_ability": [
798
+ "text2audio"
799
+ ],
434
800
  "multilingual": false,
435
- "language": "ZH"
801
+ "language": "ZH",
802
+ "model_src": {
803
+ "huggingface": {
804
+ "model_id": "myshell-ai/MeloTTS-Chinese",
805
+ "model_revision": "af5d207a364ea4208c6f589c89f57f88414bdd16"
806
+ }
807
+ }
436
808
  },
437
809
  {
810
+ "version": 2,
438
811
  "model_name": "MeloTTS-Korean",
439
812
  "model_family": "MeloTTS",
440
- "model_id": "myshell-ai/MeloTTS-Korean",
441
- "model_revision": "0207e5adfc90129a51b6b03d89be6d84360ed323",
442
- "model_ability": ["text2audio"],
813
+ "model_ability": [
814
+ "text2audio"
815
+ ],
443
816
  "multilingual": false,
444
- "language": "KR"
817
+ "language": "KR",
818
+ "model_src": {
819
+ "huggingface": {
820
+ "model_id": "myshell-ai/MeloTTS-Korean",
821
+ "model_revision": "0207e5adfc90129a51b6b03d89be6d84360ed323"
822
+ }
823
+ }
445
824
  },
446
825
  {
826
+ "version": 2,
447
827
  "model_name": "Kokoro-82M",
448
828
  "model_family": "Kokoro",
449
- "model_id": "hexgrad/Kokoro-82M",
450
- "model_revision": "7884269d6fd3f9beabc271b6f1308e5699281fa9",
451
- "model_ability": ["text2audio"],
452
- "multilingual": true
829
+ "model_ability": [
830
+ "text2audio"
831
+ ],
832
+ "multilingual": true,
833
+ "model_src": {
834
+ "huggingface": {
835
+ "model_id": "hexgrad/Kokoro-82M",
836
+ "model_revision": "7884269d6fd3f9beabc271b6f1308e5699281fa9"
837
+ },
838
+ "modelscope": {
839
+ "model_id": "AI-ModelScope/Kokoro-82M",
840
+ "model_revision": "master"
841
+ }
842
+ }
453
843
  },
454
844
  {
845
+ "version": 2,
455
846
  "model_name": "MegaTTS3",
456
847
  "model_family": "MegaTTS",
457
- "model_id": "ByteDance/MegaTTS3",
458
- "model_revision": "409a7002b006d80f0730fca6f80441b08c10e738",
459
- "model_ability": ["text2audio"],
460
- "multilingual": true
848
+ "model_ability": [
849
+ "text2audio"
850
+ ],
851
+ "multilingual": true,
852
+ "model_src": {
853
+ "huggingface": {
854
+ "model_id": "ByteDance/MegaTTS3",
855
+ "model_revision": "409a7002b006d80f0730fca6f80441b08c10e738"
856
+ },
857
+ "modelscope": {
858
+ "model_id": "ByteDance/MegaTTS3",
859
+ "model_revision": "master"
860
+ }
861
+ }
461
862
  }
462
863
  ]