Initial upload: dual deployment (ascend_310p OM + ubuntu_onnx dynamic) with shared assets

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+artifacts/ascend/ascend_310p/fm_decoder_f1537_mask_noif_mixed.om filter=lfs diff=lfs merge=lfs -text
+artifacts/ascend/ascend_310p/text_encoder_t256_p29_f3072.om filter=lfs diff=lfs merge=lfs -text

artifacts/ascend/ascend_310p/fm_decoder_f1537_mask_noif_mixed.om

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22be611d858e667e0a0d39111fa44c772f2fbdb7ff0b0ea55d708f0a469f4c6c
+size 502145530

artifacts/ascend/ascend_310p/text_encoder_t256_p29_f3072.om

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a7aa1c06d06abbb9e73d566cc63b38b25b987f13bafeee63f01241a979d287
+size 14372110

artifacts/onnx/fm_decoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4510d4f5f049f14ef80207fca695e13c820e2cea61635f402954950bc62b1e3c
+size 477534010

artifacts/onnx/text_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495eca2d5f8a911f5c361bcce5bd55cdd2508ccdd26ce3e9bf1d3c29eb974861
+size 17633735

assets/prompts/default.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706be5f309ef8e76a323a0640b288d91c6e2a62902e9a343b0e1bde507f125f1
+size 121574

assets/tokens.txt

@@ -0,0 +1,360 @@
+_	0
+^	1
+$	2
+ 	3
+!	4
+'	5
+(	6
+)	7
+,	8
+-	9
+.	10
+:	11
+;	12
+?	13
+a	14
+b	15
+c	16
+d	17
+e	18
+f	19
+h	20
+i	21
+j	22
+k	23
+l	24
+m	25
+n	26
+o	27
+p	28
+q	29
+r	30
+s	31
+t	32
+u	33
+v	34
+w	35
+x	36
+y	37
+z	38
+æ	39
+ç	40
+ð	41
+ø	42
+ħ	43
+ŋ	44
+œ	45
+ǀ	46
+ǁ	47
+ǂ	48
+ǃ	49
+ɐ	50
+ɑ	51
+ɒ	52
+ɓ	53
+ɔ	54
+ɕ	55
+ɖ	56
+ɗ	57
+ɘ	58
+ə	59
+ɚ	60
+ɛ	61
+ɜ	62
+ɞ	63
+ɟ	64
+ɠ	65
+ɡ	66
+ɢ	67
+ɣ	68
+ɤ	69
+ɥ	70
+ɦ	71
+ɧ	72
+ɨ	73
+ɪ	74
+ɫ	75
+ɬ	76
+ɭ	77
+ɮ	78
+ɯ	79
+ɰ	80
+ɱ	81
+ɲ	82
+ɳ	83
+ɴ	84
+ɵ	85
+ɶ	86
+ɸ	87
+ɹ	88
+ɺ	89
+ɻ	90
+ɽ	91
+ɾ	92
+ʀ	93
+ʁ	94
+ʂ	95
+ʃ	96
+ʄ	97
+ʈ	98
+ʉ	99
+ʊ	100
+ʋ	101
+ʌ	102
+ʍ	103
+ʎ	104
+ʏ	105
+ʐ	106
+ʑ	107
+ʒ	108
+ʔ	109
+ʕ	110
+ʘ	111
+ʙ	112
+ʛ	113
+ʜ	114
+ʝ	115
+ʟ	116
+ʡ	117
+ʢ	118
+ʲ	119
+ˈ	120
+ˌ	121
+ː	122
+ˑ	123
+˞	124
+β	125
+θ	126
+χ	127
+ᵻ	128
+ⱱ	129
+0	130
+1	131
+2	132
+3	133
+4	134
+5	135
+6	136
+7	137
+8	138
+9	139
+̧	140
+̃	141
+̪	142
+̯	143
+̩	144
+ʰ	145
+ˤ	146
+ε	147
+↓	148
+#	149
+"	150
+↑	151
+̺	152
+̻	153
+g	154
+ʦ	155
+X	156
+̝	157
+̊	158
+a1	159
+a2	160
+a3	161
+a4	162
+a5	163
+ai1	164
+ai2	165
+ai3	166
+ai4	167
+ai5	168
+an1	169
+an2	170
+an3	171
+an4	172
+an5	173
+ang1	174
+ang2	175
+ang3	176
+ang4	177
+ang5	178
+ao1	179
+ao2	180
+ao3	181
+ao4	182
+ao5	183
+b0	184
+c0	185
+ch0	186
+d0	187
+e1	188
+e2	189
+e3	190
+e4	191
+e5	192
+ei1	193
+ei2	194
+ei3	195
+ei4	196
+ei5	197
+en1	198
+en2	199
+en3	200
+en4	201
+en5	202
+eng1	203
+eng2	204
+eng3	205
+eng4	206
+eng5	207
+er2	208
+er3	209
+er4	210
+er5	211
+f0	212
+g0	213
+g2	214
+g3	215
+g4	216
+g5	217
+h0	218
+i1	219
+i2	220
+i3	221
+i4	222
+i5	223
+ia1	224
+ia2	225
+ia3	226
+ia4	227
+ia5	228
+ian1	229
+ian2	230
+ian3	231
+ian4	232
+ian5	233
+iang1	234
+iang2	235
+iang3	236
+iang4	237
+iang5	238
+iao1	239
+iao2	240
+iao3	241
+iao4	242
+iao5	243
+ie1	244
+ie2	245
+ie3	246
+ie4	247
+ie5	248
+in1	249
+in2	250
+in3	251
+in4	252
+in5	253
+ing1	254
+ing2	255
+ing3	256
+ing4	257
+ing5	258
+iong1	259
+iong2	260
+iong3	261
+iong4	262
+iu1	263
+iu2	264
+iu3	265
+iu4	266
+iu5	267
+j0	268
+k0	269
+l0	270
+m0	271
+m1	272
+m2	273
+m4	274
+m5	275
+n0	276
+n2	277
+n3	278
+n4	279
+n5	280
+ng5	281
+o1	282
+o2	283
+o3	284
+o4	285
+o5	286
+ong1	287
+ong2	288
+ong3	289
+ong4	290
+ong5	291
+ou1	292
+ou2	293
+ou3	294
+ou4	295
+ou5	296
+p0	297
+q0	298
+r0	299
+s0	300
+sh0	301
+t0	302
+u1	303
+u2	304
+u3	305
+u4	306
+u5	307
+ua1	308
+ua2	309
+ua3	310
+ua4	311
+uai1	312
+uai2	313
+uai3	314
+uai4	315
+uai5	316
+uan1	317
+uan2	318
+uan3	319
+uan4	320
+uan5	321
+uang1	322
+uang2	323
+uang3	324
+uang4	325
+uang5	326
+ue1	327
+ue2	328
+ue3	329
+ue4	330
+ui1	331
+ui2	332
+ui3	333
+ui4	334
+ui5	335
+un1	336
+un2	337
+un3	338
+un4	339
+un5	340
+uo1	341
+uo2	342
+uo3	343
+uo4	344
+uo5	345
+v2	346
+v3	347
+v4	348
+ve3	349
+ve4	350
+w0	351
+x0	352
+y0	353
+z0	354
+zh0	355
+ê1	356
+ê2	357
+ê3	358
+ê4	359

assets/vocos/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ec976ad1fd67a33ab2682d29c0ac7df85234fae875aefcc5fb215681a91b2a
+size 54365991

assets/zipvoice_310p.json

@@ -0,0 +1,20 @@
+{
+  "text_role": "text_encoder",
+  "flow_role": "flow_decoder_1537",
+  "tokens_path": "assets/tokens.txt",
+  "vocos_checkpoint_path": "assets/vocos/pytorch_model.bin",
+  "prompt_profiles": {
+    "default": "assets/prompts/default.npz"
+  },
+  "text_capacity": 256,
+  "flow_frames": 1537,
+  "num_steps": 4,
+  "t_shift": 0.5,
+  "guidance_scale": 3.0,
+  "speed": 1.0,
+  "feature_scale": 0.1,
+  "sample_rate": 24000,
+  "cross_fade_sec": 0.1,
+  "seed": 42,
+  "request_prompt_supported": false
+}

assets/zipvoice_onnx.json

@@ -0,0 +1,23 @@
+{
+  "text_encoder_path": "artifacts/onnx/text_encoder.onnx",
+  "fm_decoder_path": "artifacts/onnx/fm_decoder.onnx",
+  "tokens_path": "assets/tokens.txt",
+  "vocos_checkpoint_path": "assets/vocos/pytorch_model.bin",
+  "prompt_profiles": {
+    "default": "assets/prompts/default.npz"
+  },
+  "text_capacity": 256,
+  "num_steps": 8,
+  "t_shift": 0.5,
+  "guidance_scale": 3.0,
+  "speed": 1.0,
+  "feature_scale": 0.1,
+  "sample_rate": 24000,
+  "cross_fade_sec": 0.1,
+  "seed": 42,
+  "inter_op_num_threads": 4,
+  "intra_op_num_threads": 4,
+  "providers": [
+    "CPUExecutionProvider"
+  ]
+}

inference_manifest.json

@@ -0,0 +1,431 @@
+{
+  "schema_version": 3,
+  "model": {
+    "interface": "tensor_model",
+    "model_type": "zipvoice",
+    "operation": "synthesize",
+    "inputs": [
+      {
+        "semantic": "tts.text",
+        "dtype": "uint8",
+        "shape": [
+          -1
+        ]
+      },
+      {
+        "semantic": "tts.prompt_audio",
+        "dtype": "float32",
+        "shape": [
+          -1
+        ]
+      },
+      {
+        "semantic": "tts.prompt_sample_rate",
+        "dtype": "int64",
+        "shape": []
+      },
+      {
+        "semantic": "tts.prompt_text",
+        "dtype": "uint8",
+        "shape": [
+          -1
+        ]
+      }
+    ],
+    "outputs": [
+      {
+        "semantic": "tts.audio",
+        "dtype": "float32",
+        "shape": [
+          -1
+        ]
+      }
+    ],
+    "semantic_identity": {
+      "logical_model_revision": "zipvoice-distill-onnx-dynamic-2026-08-15",
+      "preprocessing_contract": "emilia-zh-cn2an-jieba-pypinyin-fixed-golden-prompt-v1",
+      "output_semantics": "mono-float32-pcm-24000hz-vocos-cpu"
+    }
+  },
+  "deployments": {
+    "ascend_310p": {
+      "uuid": "3775e8d7-e1d4-4f5c-9ec0-c2a062605b4c",
+      "revision": 1,
+      "artifacts": {
+        "flow_decoder_1537": {
+          "format": "om",
+          "path": "artifacts/ascend/ascend_310p/fm_decoder_f1537_mask_noif_mixed.om",
+          "sha256": "22be611d858e667e0a0d39111fa44c772f2fbdb7ff0b0ea55d708f0a469f4c6c"
+        },
+        "text_encoder": {
+          "format": "om",
+          "path": "artifacts/ascend/ascend_310p/text_encoder_t256_p29_f3072.om",
+          "sha256": "31a7aa1c06d06abbb9e73d566cc63b38b25b987f13bafeee63f01241a979d287"
+        }
+      },
+      "bindings": {
+        "flow_decoder_1537": {
+          "inputs": [
+            {
+              "dtype": "float32",
+              "index": 0,
+              "runtime_name": "t",
+              "semantic": "host.zipvoice.t",
+              "shape": []
+            },
+            {
+              "dtype": "float32",
+              "index": 1,
+              "runtime_name": "x",
+              "semantic": "host.zipvoice.flow_x",
+              "shape": [
+                1,
+                1537,
+                100
+              ]
+            },
+            {
+              "dtype": "float32",
+              "index": 2,
+              "runtime_name": "text_condition",
+              "semantic": "host.zipvoice.flow_text_condition",
+              "shape": [
+                1,
+                1537,
+                100
+              ]
+            },
+            {
+              "dtype": "float32",
+              "index": 3,
+              "runtime_name": "speech_condition",
+              "semantic": "host.zipvoice.speech_condition",
+              "shape": [
+                1,
+                1537,
+                100
+              ]
+            },
+            {
+              "dtype": "bool",
+              "index": 4,
+              "runtime_name": "padding_mask",
+              "semantic": "host.zipvoice.flow_padding_mask",
+              "shape": [
+                1,
+                1537
+              ]
+            },
+            {
+              "dtype": "float32",
+              "index": 5,
+              "runtime_name": "guidance_scale",
+              "semantic": "host.zipvoice.guidance_scale",
+              "shape": []
+            }
+          ],
+          "outputs": [
+            {
+              "dtype": "float32",
+              "index": 0,
+              "runtime_name": "PartitionedCall_/fm_decoder/Transpose_1_Transpose_2643:0:v",
+              "semantic": "host.zipvoice.velocity",
+              "shape": [
+                1,
+                1537,
+                100
+              ]
+            }
+          ]
+        },
+        "text_encoder": {
+          "inputs": [
+            {
+              "dtype": "int64",
+              "index": 0,
+              "runtime_name": "tokens",
+              "semantic": "host.zipvoice.tokens",
+              "shape": [
+                1,
+                256
+              ]
+            },
+            {
+              "dtype": "int64",
+              "index": 1,
+              "runtime_name": "tokens_len",
+              "semantic": "host.zipvoice.tokens_len",
+              "shape": []
+            },
+            {
+              "dtype": "int64",
+              "index": 2,
+              "runtime_name": "prompt_tokens",
+              "semantic": "host.zipvoice.prompt_tokens",
+              "shape": [
+                1,
+                29
+              ]
+            },
+            {
+              "dtype": "int64",
+              "index": 3,
+              "runtime_name": "prompt_features_len",
+              "semantic": "host.zipvoice.prompt_features_len",
+              "shape": []
+            },
+            {
+              "dtype": "float32",
+              "index": 4,
+              "runtime_name": "speed",
+              "semantic": "host.zipvoice.speed",
+              "shape": []
+            }
+          ],
+          "outputs": [
+            {
+              "dtype": "float32",
+              "index": 0,
+              "runtime_name": "/Where_5:0:text_condition",
+              "semantic": "host.zipvoice.text_condition",
+              "shape": [
+                1,
+                3072,
+                100
+              ]
+            },
+            {
+              "dtype": "int64",
+              "index": 1,
+              "runtime_name": "/Reshape_7:0:features_len",
+              "semantic": "host.zipvoice.features_len",
+              "shape": []
+            },
+            {
+              "dtype": "bool",
+              "index": 2,
+              "runtime_name": "/Unsqueeze_3:0:padding_mask",
+              "semantic": "host.zipvoice.padding_mask",
+              "shape": [
+                1,
+                3072
+              ]
+            }
+          ]
+        }
+      },
+      "execution": [
+        "text_encoder",
+        "flow_decoder_1537"
+      ],
+      "execution_contract": {
+        "state_scope": "request",
+        "execution_structure": "iterative",
+        "orchestration_visibility": "session",
+        "cancellation_granularity": "checkpoint"
+      },
+      "runtime_profile": {
+        "backend": "ascend",
+        "target": {
+          "runtime": "acl",
+          "runtime_abi": "cann-8.1.RC1",
+          "soc": "Ascend310P1"
+        },
+        "profile": {
+          "device_id": 0
+        }
+      }
+    },
+    "ubuntu_onnx": {
+      "uuid": "3ddcb022-42a9-4835-b2cd-636ed8ec72c4",
+      "revision": 1,
+      "artifacts": {
+        "text_encoder": {
+          "format": "onnx",
+          "path": "artifacts/onnx/text_encoder.onnx",
+          "sha256": "495eca2d5f8a911f5c361bcce5bd55cdd2508ccdd26ce3e9bf1d3c29eb974861"
+        },
+        "flow_decoder": {
+          "format": "onnx",
+          "path": "artifacts/onnx/fm_decoder.onnx",
+          "sha256": "4510d4f5f049f14ef80207fca695e13c820e2cea61635f402954950bc62b1e3c"
+        }
+      },
+      "bindings": {
+        "text_encoder": {
+          "inputs": [
+            {
+              "semantic": "host.zipvoice.tokens",
+              "dtype": "int64",
+              "index": 0,
+              "shape": [
+                1,
+                256
+              ]
+            },
+            {
+              "semantic": "host.zipvoice.tokens_len",
+              "dtype": "int64",
+              "index": 1,
+              "shape": []
+            },
+            {
+              "semantic": "host.zipvoice.prompt_tokens",
+              "dtype": "int64",
+              "index": 2,
+              "shape": [
+                1,
+                29
+              ]
+            },
+            {
+              "semantic": "host.zipvoice.prompt_features_len",
+              "dtype": "int64",
+              "index": 3,
+              "shape": []
+            },
+            {
+              "semantic": "host.zipvoice.speed",
+              "dtype": "float32",
+              "index": 4,
+              "shape": []
+            }
+          ],
+          "outputs": [
+            {
+              "semantic": "host.zipvoice.text_condition",
+              "dtype": "float32",
+              "index": 0,
+              "shape": [
+                -1,
+                100
+              ]
+            },
+            {
+              "semantic": "host.zipvoice.features_len",
+              "dtype": "int64",
+              "index": 1,
+              "shape": []
+            },
+            {
+              "semantic": "host.zipvoice.padding_mask",
+              "dtype": "float32",
+              "index": 2,
+              "shape": [
+                -1
+              ]
+            }
+          ]
+        },
+        "flow_decoder": {
+          "inputs": [
+            {
+              "semantic": "host.zipvoice.t",
+              "dtype": "float32",
+              "index": 0,
+              "shape": []
+            },
+            {
+              "semantic": "host.zipvoice.flow_x",
+              "dtype": "float32",
+              "index": 1,
+              "shape": [
+                -1,
+                100
+              ]
+            },
+            {
+              "semantic": "host.zipvoice.flow_text_condition",
+              "dtype": "float32",
+              "index": 2,
+              "shape": [
+                -1,
+                100
+              ]
+            },
+            {
+              "semantic": "host.zipvoice.speech_condition",
+              "dtype": "float32",
+              "index": 3,
+              "shape": [
+                -1,
+                100
+              ]
+            },
+            {
+              "semantic": "host.zipvoice.flow_padding_mask",
+              "dtype": "float32",
+              "index": 4,
+              "shape": [
+                -1
+              ]
+            },
+            {
+              "semantic": "host.zipvoice.guidance_scale",
+              "dtype": "float32",
+              "index": 5,
+              "shape": []
+            }
+          ],
+          "outputs": [
+            {
+              "semantic": "host.zipvoice.velocity",
+              "dtype": "float32",
+              "index": 0,
+              "shape": [
+                -1,
+                100
+              ]
+            }
+          ]
+        }
+      },
+      "execution": [
+        "text_encoder",
+        "flow_decoder"
+      ],
+      "execution_contract": {
+        "state_scope": "request",
+        "execution_structure": "iterative",
+        "orchestration_visibility": "session",
+        "cancellation_granularity": "checkpoint"
+      },
+      "runtime_profile": {
+        "backend": "torch",
+        "target": {
+          "runtime": "torch"
+        },
+        "profile": {
+          "device": "cpu"
+        }
+      }
+    }
+  },
+  "bundle": {
+    "uuid": "4a5dc0c0-6ba3-4db9-9de0-ef25689871f1",
+    "revision": 1,
+    "name": "zipvoice",
+    "files": [
+      {
+        "path": "assets/prompts/default.npz"
+      },
+      {
+        "path": "assets/tokens.txt"
+      },
+      {
+        "path": "assets/vocos/pytorch_model.bin"
+      },
+      {
+        "path": "assets/zipvoice_310p.json"
+      },
+      {
+        "path": "assets/zipvoice_onnx.json"
+      }
+    ],
+    "digest": {
+      "algorithm": "sha256",
+      "scope": "structure",
+      "value": "004a3f46987950104238f5f2f35868ba2459574064960627a1c6f9b8d5b81a50"
+    }
+  }
+}