Add verified v4.1-small-mf on-device pack

README.md

@@ -1,5 +1,5 @@
 ---
-license: mit
+license: other
 language:
   - ja
 pipeline_tag: text-to-speech
@@ -15,6 +15,7 @@ tags:
 
 ONNX model packs exported for the Onsei iOS client from the following upstream models:
 
+- [`Aratako/Irodori-TTS-v4.1-Small-MF`](https://huggingface.co/Aratako/Irodori-TTS-v4.1-Small-MF), source revision `ccc78f5d480b6e51b69b2d5042a14c4da04fea6e`
 - [`Aratako/Irodori-TTS-v4.1-Small`](https://huggingface.co/Aratako/Irodori-TTS-v4.1-Small), source revision `2b28324dc263ed5e6638b3cf3dd94c82ead07b4b`
 - [`Aratako/Irodori-TTS-500M-v3`](https://huggingface.co/Aratako/Irodori-TTS-500M-v3), source revision `236c1e56591279fc24e3c1bf6609fc06e48dde28`
 - [`Aratako/Irodori-TTS-600M-v3-VoiceDesign`](https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign), source revision `e863a3a93e652e09afeff3e84823a206a0a60314`
@@ -25,6 +26,7 @@ These files are converted runtime artifacts, not new model weights. They are not
 
 ## Packs
 
+- `v4.1-small-mf/`: MeanFlow-distilled v4.1 Small. It preserves text, Voice Design, reference-audio cloning and duration conditioning while using one conditional DiT evaluation per step. The app defaults to four steps and ignores RF-only CFG, sway, rescale and speaker-KV controls.
 - `v4.1-small/`: unified Japanese TTS, reference cloning and VoiceDesign, with the improved v4.1 duration predictor. `text_encoder.onnx` contains the shared ModernBERT backbone and both `text_state` and `caption_state` outputs. The app reuses one session for both inputs. No separate `caption_encoder.onnx` is needed. Requires the v4.1-compatible iOS client.
 - `500m-v3/`: standard Japanese TTS and reference-audio voice cloning.
 - `600m-v3-vd/`: VoiceDesign model with caption conditioning.
@@ -58,6 +60,6 @@ The ONNX export used here does not add a SilentCipher watermark. Applications us
 }
 ```
 
-## Native GPU decoder (ios-v3)
+## Native GPU decoder (ios-v3 and later)
 
-`v4.1-small/native_decoder/` contains the verified float32 Core ML decoder. New clients download it together with the ONNX pack and verify each file using SHA-256. The app measures CPU/GPU speed and numerical parity on the device before selecting the faster decoder; CPU remains the fallback. Existing `ios-v1` and `ios-v2` tags remain unchanged. The sidecar includes licenses, attribution and conversion notices.
+The v4 packs contain the verified float32 Core ML decoder. New clients download it together with the ONNX pack and verify each file using SHA-256. The app measures CPU/GPU speed and numerical parity on the device before selecting the faster decoder. Existing immutable release tags remain unchanged. The sidecar includes licenses, attribution and conversion notices.

manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
   "repository": "raratu/Onsei-iOS-Models",
-  "revision": "ios-v3",
+  "revision": "ios-v4",
   "packs": {
     "500m-v3": {
       "files": [
@@ -204,6 +204,105 @@
           "sha256": "e4ae7d4f73196a532e36ba97b9a02a9947aa52eaa5a51dd4b2975a0caa59bc5d"
         }
       ]
+    },
+    "v4.1-small-mf": {
+      "files": [
+        {
+          "path": "config.json",
+          "size": 2178,
+          "sha256": "d892d41544af570725846443c091cebb8bf7cfd687153d376128e05e58e665ee"
+        },
+        {
+          "path": "text_encoder.onnx",
+          "size": 1272933729,
+          "sha256": "961efbf4b01e47114e75b62210f29db1568acf244308c7b8657c245061fc2f39"
+        },
+        {
+          "path": "context_kv.onnx",
+          "size": 220370315,
+          "sha256": "e2a0851dab34612e1676a81316b6bc0de0ded6de27c78b8a740d6338c229adb3"
+        },
+        {
+          "path": "dit_step.onnx",
+          "size": 1272620087,
+          "sha256": "7861580d5306b1da480818f328e14ff437f2290485a87b2d1e55a79207637370"
+        },
+        {
+          "path": "duration.onnx",
+          "size": 87172678,
+          "sha256": "b807f0e9a3e86bce4fd4324db6da2ded1627f6af3ed155b918e249f2fde50809"
+        },
+        {
+          "path": "speaker_encoder.onnx",
+          "size": 242880837,
+          "sha256": "ecfa3a47f0a5bde19a4fcdca46d27fe51da97fbf68897476dca313017931945f"
+        },
+        {
+          "path": "dacvae_encode.onnx",
+          "size": 109452758,
+          "sha256": "3ccc52d3a5b7af5a7f2ade7f187e277c6f7d457b609db2206ea25b8956b34169"
+        },
+        {
+          "path": "dacvae_decode.onnx",
+          "size": 261400162,
+          "sha256": "48f55372b800130ce3f56895501fcb154bac486a9ac805da1c39ccd06e2d1e48"
+        },
+        {
+          "path": "tokenizer/tokenizer.json",
+          "size": 6718495,
+          "sha256": "6a0734cf21c802169defaffe719bc2ef12bb9d0be37e54b61ed27aa89394723d"
+        },
+        {
+          "path": "tokenizer/tokenizer_config.json",
+          "size": 668,
+          "sha256": "d229a271c64de1a7939d20d3665498e873fa91d5ee2edf135d73ec752cb9c9d3"
+        },
+        {
+          "path": "native_decoder/LICENSES/Apache-2.0.txt",
+          "size": 11359,
+          "sha256": "8c6db340475136df3c1201d458fa5755698eace76e510471ecc9d857d6083dac"
+        },
+        {
+          "path": "native_decoder/LICENSES/Descript-MIT.txt",
+          "size": 1074,
+          "sha256": "5d7a5f644313f30aad5ef032669ada67efdacefecb2c7d7b875683698bd70e87"
+        },
+        {
+          "path": "native_decoder/LICENSES/MIT.txt",
+          "size": 1064,
+          "sha256": "dfd47cc99fd79cced8e0cab04ed81f70b3d4f2f475a75746b341671bd3991c00"
+        },
+        {
+          "path": "native_decoder/LICENSES/ModernBERT-MIT.txt",
+          "size": 1070,
+          "sha256": "284353c80e0d52c06e97af62fd40e4dd1d253fa28f5d1e756121ea1d5d441509"
+        },
+        {
+          "path": "native_decoder/THIRD_PARTY_NOTICES.md",
+          "size": 3269,
+          "sha256": "c671773f21c400c2fdfa6ac14eef6f38eb72401fc309a66d539581b0d5f20b0b"
+        },
+        {
+          "path": "native_decoder/decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel",
+          "size": 73434,
+          "sha256": "a6a0e63dee65754eceac1bee3210ae88a3d17b53ffb744c27225c78ec2691593"
+        },
+        {
+          "path": "native_decoder/decoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin",
+          "size": 261380352,
+          "sha256": "738aef9a7e299ea5f5415780b2429f2f46337ec5859c0ff1d3a23b08a07fc12a"
+        },
+        {
+          "path": "native_decoder/decoder.mlpackage/Manifest.json",
+          "size": 617,
+          "sha256": "da4efa7299005d429a4603565986ed5726318adccbfe084179d193b7eb680fd6"
+        },
+        {
+          "path": "native_decoder/manifest.json",
+          "size": 1955,
+          "sha256": "e4ae7d4f73196a532e36ba97b9a02a9947aa52eaa5a51dd4b2975a0caa59bc5d"
+        }
+      ]
     }
   }
 }

v4.1-small-mf/config.json

@@ -0,0 +1,75 @@
+{
+  "model": {
+    "flow_parameterization": "meanflow",
+    "latent_dim": 32,
+    "latent_patch_size": 1,
+    "model_dim": 1280,
+    "num_layers": 12,
+    "num_heads": 20,
+    "mlp_ratio": 2.875,
+    "text_mlp_ratio": 2.6,
+    "speaker_mlp_ratio": 2.6,
+    "dropout": 0.0,
+    "text_vocab_size": 102400,
+    "text_tokenizer_repo": "sbintuitions/modernbert-ja-310m",
+    "text_encoder_revision": "77675fc96a7e445e982e2ba90246b816efc74ec6",
+    "text_add_bos": true,
+    "text_encoder_type": "pretrained",
+    "pretrained_projector_type": "residual_mlp",
+    "pretrained_projector_hidden_ratio": 2.0,
+    "pretrained_projector_dropout": 0.0,
+    "text_dim": 512,
+    "text_layers": 14,
+    "text_heads": 10,
+    "use_caption_condition": true,
+    "use_speaker_condition": true,
+    "caption_vocab_size": 102400,
+    "caption_tokenizer_repo": "sbintuitions/modernbert-ja-310m",
+    "caption_add_bos": true,
+    "caption_dim": 512,
+    "caption_layers": null,
+    "caption_heads": null,
+    "caption_mlp_ratio": null,
+    "speaker_dim": 768,
+    "speaker_layers": 8,
+    "speaker_heads": 12,
+    "speaker_patch_size": 4,
+    "timestep_embed_dim": 512,
+    "adaln_rank": 192,
+    "norm_eps": 1e-05,
+    "use_duration_predictor": true,
+    "duration_aux_dim": 14,
+    "duration_hidden_dim": 1024,
+    "duration_layers": 3,
+    "duration_dropout": 0.1,
+    "duration_attention_heads": 8,
+    "duration_architecture": "token_sum_dual_adarn_zero_no_aux",
+    "duration_token_init_frames": 9.0,
+    "duration_speaker_fusion": "adarn_zero",
+    "duration_caption_fusion": "adarn_zero",
+    "duration_caption_pooling": "masked_mean"
+  },
+  "inference": {
+    "max_text_len": 256,
+    "max_caption_len": 512,
+    "ref_max_seconds": 120.0
+  },
+  "export": {
+    "seq_len": 64,
+    "text_len": 64,
+    "caption_len": 64,
+    "ref_len": 100,
+    "sample_rate": 48000,
+    "hop_length": 1920,
+    "requires_duration": true,
+    "shared_condition_encoder": true,
+    "context_kv_cache": true,
+    "latent_dim": 32,
+    "num_layers": 12,
+    "has_caption": true,
+    "has_speaker_kv_scale": true,
+    "flow_parameterization": "meanflow",
+    "default_num_steps": 4,
+    "lora_merged": false
+  }
+}

v4.1-small-mf/context_kv.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2a0851dab34612e1676a81316b6bc0de0ded6de27c78b8a740d6338c229adb3
+size 220370315

v4.1-small-mf/dacvae_decode.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f55372b800130ce3f56895501fcb154bac486a9ac805da1c39ccd06e2d1e48
+size 261400162

v4.1-small-mf/dacvae_encode.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ccc52d3a5b7af5a7f2ade7f187e277c6f7d457b609db2206ea25b8956b34169
+size 109452758

v4.1-small-mf/dit_step.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7861580d5306b1da480818f328e14ff437f2290485a87b2d1e55a79207637370
+size 1272620087

v4.1-small-mf/duration.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b807f0e9a3e86bce4fd4324db6da2ded1627f6af3ed155b918e249f2fde50809
+size 87172678

v4.1-small-mf/native_decoder/LICENSES/Apache-2.0.txt

@@ -0,0 +1,203 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+

v4.1-small-mf/native_decoder/LICENSES/Descript-MIT.txt

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023-present, Descript
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

v4.1-small-mf/native_decoder/LICENSES/MIT.txt

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Aratako
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

v4.1-small-mf/native_decoder/LICENSES/ModernBERT-MIT.txt

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 SB Intuitions
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

v4.1-small-mf/native_decoder/THIRD_PARTY_NOTICES.md

@@ -0,0 +1,48 @@
+# Third-party notices
+
+## Irodori-TTS
+
+- v4.1 source: https://huggingface.co/Aratako/Irodori-TTS-v4.1-Small (revision `2b28324dc263ed5e6638b3cf3dd94c82ead07b4b`)
+- v4 implementation: https://github.com/Aratako/Irodori-TTS (revision `8224dafb46d0aba89209a8f905f1cb7e3299d9c1`); shared backbone export and tensor-based attention mask handling for dynamic ONNX inputs.
+- Copyright: Chihiro Arata and contributors
+- Sources: https://huggingface.co/Aratako/Irodori-TTS-500M-v3 and https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign
+- License: MIT (`LICENSES/MIT.txt`)
+- Changes: converted from PyTorch checkpoints to ONNX; split static conditioning projection into `context_kv.onnx`; fixed export dimensions for the iOS runtime.
+
+The responsible-use restrictions and disclaimers from the upstream model cards are reproduced in this repository's README.
+
+## Semantic-DACVAE-Japanese-32dim
+
+- Copyright: Chihiro Arata and contributors
+- Source: https://huggingface.co/Aratako/Semantic-DACVAE-Japanese-32dim
+- License: MIT (`LICENSES/MIT.txt`)
+- Changes: converted encoder and decoder to ONNX for the iOS runtime.
+
+## llm-jp-3-150m tokenizer
+
+- Copyright: LLM-jp / National Institute of Informatics contributors
+- Source: https://huggingface.co/llm-jp/llm-jp-3-150m
+- License: Apache License 2.0 (`LICENSES/Apache-2.0.txt`)
+- Files redistributed: tokenizer JSON and tokenizer configuration metadata.
+
+## ONNX export code
+
+- Source: https://github.com/Aratako/Irodori-TTS
+- License: MIT (`LICENSES/MIT.txt`)
+
+## ModernBERT-ja-310m (v4.1 encoder and tokenizer)
+
+- Source: https://huggingface.co/sbintuitions/modernbert-ja-310m
+- Copyright: SB Intuitions and contributors
+- License: MIT
+- The fine-tuned encoder and exact tokenizer are redistributed as part of the Irodori-TTS-v4.1-Small conversion. Text and caption share one encoder graph.
+
+## DACVAE / Descript Audio Codec ancestry (ONNX and Core ML)
+
+- Semantic-DACVAE-Japanese-32dim source revision: `47376ee24834d7a05a48ebabfe3cde29b3c5e214` (MIT as declared by its model card).
+- Base weights: https://huggingface.co/facebook/dacvae-watermarked (model metadata: Apache-2.0).
+- DACVAE implementation: https://github.com/facebookresearch/dacvae (Apache License 2.0; `LICENSES/Apache-2.0.txt`). Copyright (c) Meta Platforms, Inc. and affiliates. All Rights Reserved.
+- DAC architecture: https://github.com/descriptinc/descript-audio-codec (MIT; `LICENSES/Descript-MIT.txt`). Copyright (c) 2023-present, Descript.
+- The base model README also contains a conflicting “SAM License” sentence; the linked DACVAE implementation LICENSE is Apache-2.0. This distribution preserves the Apache-2.0 license and does not relicense upstream components as MIT.
+- Changes by the Onsei conversion: exported the decoder to a float32 Core ML ML Program using coremltools 9.0, folded weight normalization, froze constant expressions, and bounded batch/time input dimensions. No quantization or retraining. Watermarking remains bypassed as instructed by the Japanese model card. The converted model is not a watermarked-audio guarantee.
+- `native_decoder/manifest.json` records the source ONNX digest, converted file digests and numerical verification. Core ML conversion does not grant any additional rights to upstream weights.

v4.1-small-mf/native_decoder/decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a0e63dee65754eceac1bee3210ae88a3d17b53ffb744c27225c78ec2691593
+size 73434

v4.1-small-mf/native_decoder/decoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:738aef9a7e299ea5f5415780b2429f2f46337ec5859c0ff1d3a23b08a07fc12a
+size 261380352

v4.1-small-mf/native_decoder/decoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "7F8C5BAD-4A0B-409B-AB3F-56CDF9F6EE74": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "8051F718-3344-4CAA-9D19-13AF2C5E5770": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "7F8C5BAD-4A0B-409B-AB3F-56CDF9F6EE74"
+}

v4.1-small-mf/native_decoder/manifest.json

@@ -0,0 +1,73 @@
+{
+  "version": 1,
+  "source_sha256": "48f55372b800130ce3f56895501fcb154bac486a9ac805da1c39ccd06e2d1e48",
+  "precision": "float32",
+  "latent_dim": 32,
+  "hop_length": 1920,
+  "max_batch": 2,
+  "max_steps": 42,
+  "files": {
+    "decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel": "a6a0e63dee65754eceac1bee3210ae88a3d17b53ffb744c27225c78ec2691593",
+    "decoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin": "738aef9a7e299ea5f5415780b2429f2f46337ec5859c0ff1d3a23b08a07fc12a",
+    "decoder.mlpackage/Manifest.json": "da4efa7299005d429a4603565986ed5726318adccbfe084179d193b7eb680fd6"
+  },
+  "verified": true,
+  "verification": [
+    {
+      "batch": 1,
+      "steps": 1,
+      "scale": 1,
+      "max_abs_error": 2.2351741790771484e-07,
+      "snr_db": 113.25527451540609,
+      "seconds": 1.1235392090020468
+    },
+    {
+      "batch": 1,
+      "steps": 17,
+      "scale": 0.1,
+      "max_abs_error": 1.1958181858062744e-06,
+      "snr_db": 103.40947763285638,
+      "seconds": 0.23017945799801964
+    },
+    {
+      "batch": 1,
+      "steps": 24,
+      "scale": 0.5,
+      "max_abs_error": 1.5362165868282318e-06,
+      "snr_db": 109.4220824061057,
+      "seconds": 0.16355833299894584
+    },
+    {
+      "batch": 1,
+      "steps": 42,
+      "scale": 1,
+      "max_abs_error": 1.7881393432617188e-06,
+      "snr_db": 112.85191583449021,
+      "seconds": 0.28804241699981503
+    },
+    {
+      "batch": 2,
+      "steps": 1,
+      "scale": 1,
+      "max_abs_error": 4.6193599700927734e-07,
+      "snr_db": 113.08896145092076,
+      "seconds": 0.8671291659993585
+    },
+    {
+      "batch": 2,
+      "steps": 24,
+      "scale": 1,
+      "max_abs_error": 2.8833746910095215e-06,
+      "snr_db": 111.97978153776847,
+      "seconds": 0.3601945829941542
+    },
+    {
+      "batch": 1,
+      "steps": 42,
+      "scale": 0,
+      "max_abs_error": 9.350478649139404e-07,
+      "snr_db": 103.19954312276388,
+      "seconds": 0.28257145800307626
+    }
+  ]
+}

v4.1-small-mf/speaker_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecfa3a47f0a5bde19a4fcdca46d27fe51da97fbf68897476dca313017931945f
+size 242880837

v4.1-small-mf/text_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:961efbf4b01e47114e75b62210f29db1568acf244308c7b8657c245061fc2f39
+size 1272933729

v4.1-small-mf/tokenizer/tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "add_dummy_prefix_space": false,
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "is_local": false,
+  "keep_accents": true,
+  "legacy": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "<sep>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}