RUAccentCoreML on-device bundle: 4 CoreML models + .rapack dicts + tokenizers

.gitattributes

@@ -33,3 +33,6 @@ 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
+dictpack/accents.rapack filter=lfs diff=lfs merge=lfs -text
+dictpack/omographs.rapack filter=lfs diff=lfs merge=lfs -text
+dictpack/yo_words.rapack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,28 @@
+---
+license: apache-2.0
+tags:
+  - coreml
+  - russian
+  - text-to-speech
+  - accentuation
+  - ruaccent
+---
+
+# RUAccentCoreML — on-device resource bundle
+
+CoreML port of [RUAccent](https://github.com/Den4ikAI/ruaccent) (Russian lexical stress,
+variant `turbo3.1`) for the Swift package
+[`RUAccentCoreML`](https://github.com/iliasaz/ruaccent-coreml). Downloaded on-device by
+`ModelRepository.download()` (swift-transformers `HubApi.snapshot`) and consumed by
+`RUAccent(modelDirectory:)`.
+
+**Layout**
+- `coreml/` — the four CoreML models (fp16; M2/M3 8-bit palettized):
+  M1 accent (RoFormer), M2 omograph (BERT cross-encoder), M3 stress-usage (BERT),
+  M4 yo-homograph (DistilBERT).
+- `dictpack/` — packed dictionaries (`.rapack` v2, mmap-able): full `accents` (3.19M entries),
+  `omographs`, `yo_words`, `yo_homographs`.
+- `nn/` — the minimal tokenizer files (vocab/merges) the Swift tokenizers read.
+
+Weights/dicts are the apache-2.0 HF `ruaccent/accentuator` artifacts, re-packaged. The pipeline
+code is an independent reimplementation (the upstream Python is CC BY-NC-ND and was not copied).

coreml/M1_accent_fp16.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a4d3c2705fd489dcc6571b03a4a0818d8f2411cd9327f5efe7688438189ee5
+size 74982

coreml/M1_accent_fp16.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586eaa768f4b3cfcb03d0c7a4528ee4d477b40e274c9129918f6b870f1ff3d56
+size 1080832

coreml/M1_accent_fp16.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "2BC01821-A8F7-4E76-8465-88CA1BE31553": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "97E28DEC-745C-44A0-8E9C-8CBB7FC3EA35": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "2BC01821-A8F7-4E76-8465-88CA1BE31553"
+}

coreml/M2_omograph_fp16_pal8.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6670bff74000b62ca5d187c5114a9968e21f9b92b5d31d803474a38027b2757a
+size 95704

coreml/M2_omograph_fp16_pal8.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c8276392a716df8fb2a35fcc4c52e9b8a59dc4d4f8264b7609482d31ab42520
+size 89874624

coreml/M2_omograph_fp16_pal8.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "0DCDC2B9-090C-4564-A4B3-F1D74FAE62C3": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "3001CB24-7EE7-4B3D-9183-84A8A905DF2A": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "3001CB24-7EE7-4B3D-9183-84A8A905DF2A"
+}

coreml/M3_stress_fp16_pal8.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4399d9595fb1c3b12cb9431f5a995985553d1c5ec85f4bd1fdb27b2772c7a520
+size 44231

coreml/M3_stress_fp16_pal8.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e11e0a0a6ea88630734ac579a164df19ef2fad4481d78ed388f92d3e45b7ec
+size 29133328

coreml/M3_stress_fp16_pal8.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "034191E6-3570-4B08-9819-2212A6B92ED3": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "7CB93492-DF00-4252-B8E7-985EFAFFBC3A": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "034191E6-3570-4B08-9819-2212A6B92ED3"
+}

coreml/M4_yo_fp16.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b453b66db9b495afc4e61aaaca6f814f99b240a847c4d41cac9cc4a754b71cc5
+size 40953

coreml/M4_yo_fp16.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceec8ca0536bf7e622ea6f333a47db829744121c8b4a5f046ebeedaff94c3058
+size 7137136

coreml/M4_yo_fp16.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "7511B755-CEC7-4781-A121-94257689CBA4": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "A3DF6966-BDE5-43B7-BE4F-9CCC6CA4C36B": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "A3DF6966-BDE5-43B7-BE4F-9CCC6CA4C36B"
+}

dictpack/accents.rapack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e119e12f12cfc41cb155549ea2d824f2bc4e5c1ab4de2f97c7dc6044d921b905
+size 22801810

dictpack/omographs.rapack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16e99395d9d62d6a1d1c65e8a2a6bf9f60c4fed2925d35d9068a9c69362dec9
+size 978030

dictpack/yo_words.rapack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec6a9c963b6eff92574e577e846d49228a8db65f62cba0d65452f495c03acfa
+size 1050163

nn/nn_accent/vocab.txt

@@ -0,0 +1,45 @@
+[pad]
+[unk]
+[bos]
+[eos]
+'
+-
+.
+?
+`
+c
+e
+́
+а
+б
+в
+г
+д
+е
+ж
+з
+и
+й
+к
+л
+м
+н
+о
+п
+р
+с
+т
+у
+ф
+х
+ц
+ч
+ш
+щ
+ъ
+ы
+ь
+э
+ю
+я
+ё