Publish prebuilt Phonemis ONNX frontends v2.1.0

README.md

@@ -30,7 +30,7 @@ tags:
 # Complete Kokoro catalog for ONNX Runtime and Kotlin Multiplatform
 
 All 157 voices published in the pinned official Kokoro v1.0 and v1.1-zh repositories, plus the
-native Polish and German voices, converted for on-device ONNX Runtime use. Version 2.0.0 contains
+native Polish and German voices, converted for on-device ONNX Runtime use. Version 2.1.0 contains
 **159 voices**, **10 languages / 11 locale profiles**, and **4 compatible FP32 models**.
 
 The catalog is designed for a language picker followed by a voice picker. A client downloads only
@@ -59,7 +59,7 @@ voices introduced with v1.1-zh are included as well and correctly point to that
 
 ## Download-on-demand client flow
 
-1. Fetch [`catalog.json`](catalog.json) from the immutable `v2.0.0` revision.
+1. Fetch [`catalog.json`](catalog.json) from the immutable `v2.1.0` revision.
 2. Show `languages`, then the selected language's `voices`.
 3. Read the selected voice's `modelId` and resolve it in top-level `models`.
 4. Resolve that model's `tokenizerId` in top-level `tokenizers`.
@@ -68,7 +68,7 @@ voices introduced with v1.1-zh are included as well and correctly point to that
 6. Verify each file's `sizeBytes` and `sha256` before activating it.
 7. Cache by artifact path or SHA-256 so shared models are not downloaded again.
 
-Resolve every artifact path relative to the catalog URL. Pinning the catalog to `v2.0.0` therefore
+Resolve every artifact path relative to the catalog URL. Pinning the catalog to `v2.1.0` therefore
 pins every dependent file to the same immutable release. The schema is versioned at
 [`schema/kokoro-catalog.schema.json`](schema/kokoro-catalog.schema.json).
 
@@ -95,10 +95,10 @@ combining marks such as the nasalization mark in `ɔ̃` are separate code points
 ## Text frontends
 
 Phonemis assets are bundled for `en-us`, `en-gb`, `de`, `fr`, `es`, `it`, `pl`, `pt`, and `hi`.
-They produce Kokoro-compatible IPA without shipping eSpeak or a GPL component. English packs also
-include the full lexicon and part-of-speech tagger required for best results. Phonemis itself is a
-small C++20 library; Android/JVM can expose it through a native bridge and Web can use an
-Emscripten/Wasm build.
+Version 2.1.0 publishes each neural frontend as a ready-to-open ONNX graph, so clients no longer
+need to convert the upstream weight container at runtime. They produce Kokoro-compatible IPA
+without shipping eSpeak or a GPL component. English packs also include the full lexicon and
+part-of-speech tagger required for best results.
 
 Japanese and Mandarin model/voice packs are fully included and accept phoneme input. Their
 official Python path uses `misaki[ja]` and `misaki[zh]`, but this repository does not pretend those
@@ -110,7 +110,8 @@ distributed here.
 
 ## Validation
 
-Version 2.0.0 validation covers:
+Version 2.1.0 preserves the complete 2.0.0 validation baseline and additionally validates all nine
+prebuilt Phonemis graphs with ONNX Runtime 1.29 CPU inference. Validation covers:
 
 - JSON Schema and SHA-256 verification for all 183 catalog artifacts;
 - ONNX structural validation and Apache-2.0/source metadata checks for all 4 models;
@@ -118,6 +119,8 @@ Version 2.0.0 validation covers:
 - 13 natural-language cases covering every profile and both Chinese model generations;
 - 1-, 128-, and 510-phoneme boundary cases for each model;
 - ONNX Runtime Web 1.29 WebAssembly inference for each model, including the 510-phoneme boundary.
+- deterministic prebuilding, size/SHA-256 verification, and a real inference smoke for every
+  bundled Phonemis ONNX frontend.
 
 Results are recorded in [`validation/package-validation.json`](validation/package-validation.json)
 and the `validation/web-*.json` files. Actual frontend outputs are recorded in
@@ -145,7 +148,7 @@ fixed voice-count assertions. Source and converted hashes are recorded in
 Maintainers can publish a fully validated folder after authenticating with the Hugging Face CLI:
 
 ```bash
-python scripts/publish_hf.py <namespace>/kokoro-kmp-models --tag v2.0.0
+python scripts/publish_hf.py <namespace>/kokoro-kmp-models --tag v2.1.0
 ```
 
 ## Scope and compatibility

SOURCES.lock.json

@@ -38,6 +38,11 @@
     "languageProfileCount": 9,
     "artifactCount": 13
   },
+  "phonemisOnnx": {
+    "manifestPath": "sources/phonemis-onnx-v2.1.0.json",
+    "manifestSha256": "6462bbecbad96b69446aca7cf594c67a6435ba06f2e199d2249285abf273a283",
+    "artifactCount": 9
+  },
   "upstreamAssetManifest": {
     "path": "sources/upstream-assets.json",
     "sha256": "3f6df7a5819dbb96b6ab740cdd6f4ba2501ccdee1e633cdd050ef0b4912c009e",

THIRD_PARTY_NOTICES.md

@@ -28,6 +28,10 @@ plus the English full lexicons and tagger models, come from
 [`IgorSwat/Phonemis`](https://github.com/IgorSwat/Phonemis), revision
 `71eb1ce33bd586d38cbac037843b8539d7829c3b`.
 
+For release `v2.1.0`, the nine neural weight containers are deterministically wrapped as ONNX
+graphs ahead of distribution. Exact source and output hashes, sizes, and converter provenance are
+recorded in [`sources/phonemis-onnx-v2.1.0.json`](sources/phonemis-onnx-v2.1.0.json).
+
 Phonemis is distributed under the MIT License. Its unchanged license text is available in
 [`third-party/phonemis/LICENSE`](third-party/phonemis/LICENSE). This separate MIT license applies
 to the Phonemis files and does not alter Kokoro's Apache-2.0 license.

catalog.json

@@ -1,7 +1,7 @@
 {
   "$schema": "schema/kokoro-catalog.schema.json",
   "schemaVersion": 2,
-  "catalogVersion": "2.0.0",
+  "catalogVersion": "2.1.0",
   "distribution": {
     "provider": "huggingface",
     "repository": "Shusek00/kokoro-kmp-models",
@@ -219,10 +219,10 @@
           {
             "role": "neural-model",
             "artifact": {
-              "path": "phonemizers/en-us/phonemizer_en_us.bin",
-              "mediaType": "application/octet-stream",
-              "sizeBytes": 7094120,
-              "sha256": "e059561fb8d51eadfd2000965be30e31f0152e7e8c8b4fcf7859dbcce8557576"
+              "path": "phonemizers/en-us/phonemizer_en_us.onnx",
+              "mediaType": "application/onnx",
+              "sizeBytes": 7105527,
+              "sha256": "479cd9d89819a60c4f8609dbb116ae5b362d46c0c592b97605968cbaef1e7bc6"
             }
           },
           {
@@ -529,10 +529,10 @@
           {
             "role": "neural-model",
             "artifact": {
-              "path": "phonemizers/en-gb/phonemizer_en_gb.bin",
-              "mediaType": "application/octet-stream",
-              "sizeBytes": 7094120,
-              "sha256": "3d4fe5a541c02de30879a5b84b88f5229f5b31f8fb2dcf7e89a1ce3a6c330334"
+              "path": "phonemizers/en-gb/phonemizer_en_gb.onnx",
+              "mediaType": "application/onnx",
+              "sizeBytes": 7105527,
+              "sha256": "065baba624db8391905e53c78706a12c5f4cba12a77e62a90900b2113bdb17e7"
             }
           },
           {
@@ -683,10 +683,10 @@
           {
             "role": "neural-model",
             "artifact": {
-              "path": "phonemizers/es/phonemizer_es.bin",
-              "mediaType": "application/octet-stream",
-              "sizeBytes": 7094120,
-              "sha256": "8dc68946e12c1a233ac9153fd369f6418b930a3d731587ff64dc789f44d75a52"
+              "path": "phonemizers/es/phonemizer_es.onnx",
+              "mediaType": "application/onnx",
+              "sizeBytes": 7105527,
+              "sha256": "0437232bb50cffdefc51995dc8195c14992b185655e3bc0f0005b97a7f162240"
             }
           }
         ]
@@ -747,10 +747,10 @@
           {
             "role": "neural-model",
             "artifact": {
-              "path": "phonemizers/fr/phonemizer_fr.bin",
-              "mediaType": "application/octet-stream",
-              "sizeBytes": 7094120,
-              "sha256": "fa0018b750a3670328026107b44e02eafe3223b6878585ca0927786b7812d96a"
+              "path": "phonemizers/fr/phonemizer_fr.onnx",
+              "mediaType": "application/onnx",
+              "sizeBytes": 7105527,
+              "sha256": "d0ca22d75569827f86d73bd8f071a128e478d4f6f107e94035236ba080658485"
             }
           }
         ]
@@ -787,10 +787,10 @@
           {
             "role": "neural-model",
             "artifact": {
-              "path": "phonemizers/hi/phonemizer_hi.bin",
-              "mediaType": "application/octet-stream",
-              "sizeBytes": 9194344,
-              "sha256": "dcee3272f96d7f1b7cc40c5df23060b502a5b9066f7cb20092413dff82a487f5"
+              "path": "phonemizers/hi/phonemizer_hi.onnx",
+              "mediaType": "application/onnx",
+              "sizeBytes": 9205753,
+              "sha256": "7e046cd695d2615bad723b24e7fbe0339594526f6953df4c5d20aa53862a9678"
             }
           }
         ]
@@ -863,10 +863,10 @@
           {
             "role": "neural-model",
             "artifact": {
-              "path": "phonemizers/it/phonemizer_it.bin",
-              "mediaType": "application/octet-stream",
-              "sizeBytes": 7094120,
-              "sha256": "dca8d068d76134a40856cd874ea6e5e05c988914369ab643f52ab77a512067e3"
+              "path": "phonemizers/it/phonemizer_it.onnx",
+              "mediaType": "application/onnx",
+              "sizeBytes": 7105527,
+              "sha256": "30c115355c28c1c8657eba91a1557d89b9bb69b373202399546719cf2991f9f8"
             }
           }
         ]
@@ -991,10 +991,10 @@
           {
             "role": "neural-model",
             "artifact": {
-              "path": "phonemizers/pt-br/phonemizer_pt.bin",
-              "mediaType": "application/octet-stream",
-              "sizeBytes": 7094120,
-              "sha256": "89049ea03c52ffa7233a343d44a35059aae3b1231d772c8c498fbc4427756ecf"
+              "path": "phonemizers/pt-br/phonemizer_pt.onnx",
+              "mediaType": "application/onnx",
+              "sizeBytes": 7105527,
+              "sha256": "fb30ed5fbdf2465b5f3d8a08903d2cc50dfa77b4c4c24518ac0ba26640393f52"
             }
           }
         ]
@@ -2367,10 +2367,10 @@
           {
             "role": "neural-model",
             "artifact": {
-              "path": "phonemizers/pl/phonemizer_pl.bin",
-              "mediaType": "application/octet-stream",
-              "sizeBytes": 7094120,
-              "sha256": "ec85f4dc2c4ac7a72ff88b98b0664a4ed887bd15c0d5add2eb1d6a6ee05b73f2"
+              "path": "phonemizers/pl/phonemizer_pl.onnx",
+              "mediaType": "application/onnx",
+              "sizeBytes": 7105527,
+              "sha256": "4cdbafd810ed3cad701c24380894115f848cfa39602d731e7a8e085adee62233"
             }
           }
         ]
@@ -2407,10 +2407,10 @@
           {
             "role": "neural-model",
             "artifact": {
-              "path": "phonemizers/de/phonemizer_de.bin",
-              "mediaType": "application/octet-stream",
-              "sizeBytes": 7094120,
-              "sha256": "4888dc7e54dc66098551555096562063364091fc246da0d057b629587bedaa0b"
+              "path": "phonemizers/de/phonemizer_de.onnx",
+              "mediaType": "application/onnx",
+              "sizeBytes": 7105527,
+              "sha256": "aef1d8a6163b426733059f35f406c540ccd08a3f7855eebe6a09ab4908d5dac7"
             }
           }
         ]

catalog.template.json

@@ -1,7 +1,7 @@
 {
   "$schema": "schema/kokoro-catalog.schema.json",
   "schemaVersion": 2,
-  "catalogVersion": "2.0.0",
+  "catalogVersion": "2.1.0",
   "distribution": {
     "provider": "huggingface",
     "repository": "Shusek00/kokoro-kmp-models",
@@ -183,7 +183,7 @@
         "artifacts": [
           {
             "role": "neural-model",
-            "artifact": { "$artifact": { "path": "phonemizers/en-us/phonemizer_en_us.bin", "mediaType": "application/octet-stream" } }
+            "artifact": { "$artifact": { "path": "phonemizers/en-us/phonemizer_en_us.onnx", "mediaType": "application/onnx" } }
           },
           {
             "role": "lexicon",
@@ -214,7 +214,7 @@
         "artifacts": [
           {
             "role": "neural-model",
-            "artifact": { "$artifact": { "path": "phonemizers/en-gb/phonemizer_en_gb.bin", "mediaType": "application/octet-stream" } }
+            "artifact": { "$artifact": { "path": "phonemizers/en-gb/phonemizer_en_gb.onnx", "mediaType": "application/onnx" } }
           },
           {
             "role": "lexicon",
@@ -245,7 +245,7 @@
         "artifacts": [
           {
             "role": "neural-model",
-            "artifact": { "$artifact": { "path": "phonemizers/es/phonemizer_es.bin", "mediaType": "application/octet-stream" } }
+            "artifact": { "$artifact": { "path": "phonemizers/es/phonemizer_es.onnx", "mediaType": "application/onnx" } }
           }
         ]
       },
@@ -268,7 +268,7 @@
         "artifacts": [
           {
             "role": "neural-model",
-            "artifact": { "$artifact": { "path": "phonemizers/fr/phonemizer_fr.bin", "mediaType": "application/octet-stream" } }
+            "artifact": { "$artifact": { "path": "phonemizers/fr/phonemizer_fr.onnx", "mediaType": "application/onnx" } }
           }
         ]
       },
@@ -291,7 +291,7 @@
         "artifacts": [
           {
             "role": "neural-model",
-            "artifact": { "$artifact": { "path": "phonemizers/hi/phonemizer_hi.bin", "mediaType": "application/octet-stream" } }
+            "artifact": { "$artifact": { "path": "phonemizers/hi/phonemizer_hi.onnx", "mediaType": "application/onnx" } }
           }
         ]
       },
@@ -314,7 +314,7 @@
         "artifacts": [
           {
             "role": "neural-model",
-            "artifact": { "$artifact": { "path": "phonemizers/it/phonemizer_it.bin", "mediaType": "application/octet-stream" } }
+            "artifact": { "$artifact": { "path": "phonemizers/it/phonemizer_it.onnx", "mediaType": "application/onnx" } }
           }
         ]
       },
@@ -353,7 +353,7 @@
         "artifacts": [
           {
             "role": "neural-model",
-            "artifact": { "$artifact": { "path": "phonemizers/pt-br/phonemizer_pt.bin", "mediaType": "application/octet-stream" } }
+            "artifact": { "$artifact": { "path": "phonemizers/pt-br/phonemizer_pt.onnx", "mediaType": "application/onnx" } }
           }
         ]
       },
@@ -392,7 +392,7 @@
         "artifacts": [
           {
             "role": "neural-model",
-            "artifact": { "$artifact": { "path": "phonemizers/pl/phonemizer_pl.bin", "mediaType": "application/octet-stream" } }
+            "artifact": { "$artifact": { "path": "phonemizers/pl/phonemizer_pl.onnx", "mediaType": "application/onnx" } }
           }
         ]
       },
@@ -427,7 +427,7 @@
         "artifacts": [
           {
             "role": "neural-model",
-            "artifact": { "$artifact": { "path": "phonemizers/de/phonemizer_de.bin", "mediaType": "application/octet-stream" } }
+            "artifact": { "$artifact": { "path": "phonemizers/de/phonemizer_de.onnx", "mediaType": "application/onnx" } }
           }
         ]
       },

phonemizers/de/phonemizer_de.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef1d8a6163b426733059f35f406c540ccd08a3f7855eebe6a09ab4908d5dac7
+size 7105527

phonemizers/en-gb/phonemizer_en_gb.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065baba624db8391905e53c78706a12c5f4cba12a77e62a90900b2113bdb17e7
+size 7105527

phonemizers/en-us/phonemizer_en_us.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479cd9d89819a60c4f8609dbb116ae5b362d46c0c592b97605968cbaef1e7bc6
+size 7105527

phonemizers/es/phonemizer_es.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0437232bb50cffdefc51995dc8195c14992b185655e3bc0f0005b97a7f162240
+size 7105527

phonemizers/fr/phonemizer_fr.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ca22d75569827f86d73bd8f071a128e478d4f6f107e94035236ba080658485
+size 7105527

phonemizers/hi/phonemizer_hi.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e046cd695d2615bad723b24e7fbe0339594526f6953df4c5d20aa53862a9678
+size 9205753

phonemizers/it/phonemizer_it.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c115355c28c1c8657eba91a1557d89b9bb69b373202399546719cf2991f9f8
+size 7105527

phonemizers/pl/phonemizer_pl.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cdbafd810ed3cad701c24380894115f848cfa39602d731e7a8e085adee62233
+size 7105527

phonemizers/pt-br/phonemizer_pt.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb30ed5fbdf2465b5f3d8a08903d2cc50dfa77b4c4c24518ac0ba26640393f52
+size 7105527

scripts/publish_hf.py

@@ -25,7 +25,7 @@ def run_validation(skip_web: bool) -> None:
 def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser()
     parser.add_argument("repo_id", help="Hugging Face repo, e.g. username/kokoro-kmp-models")
-    parser.add_argument("--tag", default="v2.0.0")
+    parser.add_argument("--tag", default="v2.1.0")
     parser.add_argument("--skip-web-validation", action="store_true")
     return parser.parse_args()
 

scripts/validate_package.py

@@ -138,6 +138,33 @@ if (
     raise RuntimeError("SOURCES.lock.json does not match the upstream asset manifest")
 if source_inventory["voiceCount"] != 157 or source_inventory["catalogVoiceCount"] != 159:
     raise RuntimeError("Pinned upstream inventory must contain exactly 157 voices")
+
+phonemis_onnx_lock = source_lock["phonemisOnnx"]
+phonemis_onnx_manifest_path = ROOT / phonemis_onnx_lock["manifestPath"]
+if phonemis_onnx_lock["manifestSha256"] != sha256(phonemis_onnx_manifest_path):
+    raise RuntimeError("SOURCES.lock.json does not match the Phonemis ONNX manifest")
+phonemis_onnx_manifest = json.loads(
+    phonemis_onnx_manifest_path.read_text(encoding="utf-8")
+)
+if len(phonemis_onnx_manifest["artifacts"]) != phonemis_onnx_lock["artifactCount"]:
+    raise RuntimeError("Phonemis ONNX manifest artifact count mismatch")
+phonemis_sources = {
+    item["artifactPath"]: item for item in source_inventory["phonemis"]
+}
+for converted in phonemis_onnx_manifest["artifacts"]:
+    source = phonemis_sources.get(converted["sourcePath"])
+    if source is None or source["sourceSha256"] != converted["sourceSha256"]:
+        raise RuntimeError(
+            f"Phonemis ONNX source mismatch for {converted['sourcePath']}"
+        )
+    artifact = artifact_by_path.get(converted["path"])
+    if artifact is None or any(
+        artifact[field] != converted[field]
+        for field in ("path", "sizeBytes", "sha256")
+    ):
+        raise RuntimeError(
+            f"Phonemis ONNX catalog mismatch for {converted['path']}"
+        )
 for source_voice in source_inventory["voices"]:
     key = (source_voice["languageId"], source_voice["id"])
     if key not in voices:
@@ -176,6 +203,38 @@ bundled_languages = {
     for language in languages.values()
     if language["textFrontend"]["status"] == "bundled"
 }
+frontend_onnx_results = []
+frontend_session_options = ort.SessionOptions()
+frontend_session_options.graph_optimization_level = ort.GraphOptimizationLevel.ORT_ENABLE_ALL
+for language_id, language in bundled_languages.items():
+    neural_model = next(
+        item["artifact"]
+        for item in language["textFrontend"]["artifacts"]
+        if item["role"] == "neural-model"
+    )
+    if neural_model.get("mediaType") != "application/onnx":
+        raise RuntimeError(f"{language_id}: neural frontend is not a prebuilt ONNX model")
+    frontend_session = ort.InferenceSession(
+        str(ROOT / neural_model["path"]),
+        sess_options=frontend_session_options,
+        providers=["CPUExecutionProvider"],
+    )
+    logits = frontend_session.run(
+        ["logits"],
+        {"input_ids": np.asarray([[2]], dtype=np.int64)},
+    )[0]
+    if logits.ndim != 3 or logits.shape[0] != 1 or logits.shape[2] != 116:
+        raise RuntimeError(f"{language_id}: unexpected frontend logits shape {logits.shape}")
+    if not np.isfinite(logits).all():
+        raise RuntimeError(f"{language_id}: non-finite frontend logits")
+    frontend_onnx_results.append(
+        {
+            "language": language_id,
+            "path": neural_model["path"],
+            "sha256": neural_model["sha256"],
+            "logitsShape": list(logits.shape),
+        }
+    )
 phonemis_languages = {
     case["language"] for case in frontend_validation["phonemis"]["cases"]
 }
@@ -327,6 +386,8 @@ report = {
     "languageProfilesValidated": len(languages),
     "voicesValidated": len(voice_results),
     "frontendCasesValidated": len(frontend_cases),
+    "frontendOnnxModelsValidated": len(frontend_onnx_results),
+    "frontendOnnxSmokeTests": frontend_onnx_results,
     "cases": case_results,
     "voiceSmokeTests": voice_results,
     "boundaryCases": boundary_results,
@@ -344,6 +405,7 @@ print(
             "languageProfilesValidated": report["languageProfilesValidated"],
             "voicesValidated": report["voicesValidated"],
             "frontendCasesValidated": report["frontendCasesValidated"],
+            "frontendOnnxModelsValidated": report["frontendOnnxModelsValidated"],
             "naturalCasesValidated": len(case_results),
             "boundaryCasesValidated": len(boundary_results),
         },

sources/phonemis-onnx-v2.1.0.json

@@ -0,0 +1,21 @@
+{
+  "schemaVersion": 1,
+  "converter": {
+    "repository": "ShinudaCommunity/kokoro-narrator-suvio-plugin",
+    "revision": "d16c577a516feac9ce0459bd615fd3a847a4334e",
+    "sourcePath": "src/commonMain/kotlin/PhonemisOnnx.kt",
+    "converterVersion": "1",
+    "producer": "Suvio Kokoro Narrator 0.1.0"
+  },
+  "artifacts": [
+    {"language": "en-us", "sourcePath": "phonemizers/en-us/phonemizer_en_us.bin", "sourceSha256": "e059561fb8d51eadfd2000965be30e31f0152e7e8c8b4fcf7859dbcce8557576", "path": "phonemizers/en-us/phonemizer_en_us.onnx", "sizeBytes": 7105527, "sha256": "479cd9d89819a60c4f8609dbb116ae5b362d46c0c592b97605968cbaef1e7bc6"},
+    {"language": "en-gb", "sourcePath": "phonemizers/en-gb/phonemizer_en_gb.bin", "sourceSha256": "3d4fe5a541c02de30879a5b84b88f5229f5b31f8fb2dcf7e89a1ce3a6c330334", "path": "phonemizers/en-gb/phonemizer_en_gb.onnx", "sizeBytes": 7105527, "sha256": "065baba624db8391905e53c78706a12c5f4cba12a77e62a90900b2113bdb17e7"},
+    {"language": "es", "sourcePath": "phonemizers/es/phonemizer_es.bin", "sourceSha256": "8dc68946e12c1a233ac9153fd369f6418b930a3d731587ff64dc789f44d75a52", "path": "phonemizers/es/phonemizer_es.onnx", "sizeBytes": 7105527, "sha256": "0437232bb50cffdefc51995dc8195c14992b185655e3bc0f0005b97a7f162240"},
+    {"language": "fr", "sourcePath": "phonemizers/fr/phonemizer_fr.bin", "sourceSha256": "fa0018b750a3670328026107b44e02eafe3223b6878585ca0927786b7812d96a", "path": "phonemizers/fr/phonemizer_fr.onnx", "sizeBytes": 7105527, "sha256": "d0ca22d75569827f86d73bd8f071a128e478d4f6f107e94035236ba080658485"},
+    {"language": "hi", "sourcePath": "phonemizers/hi/phonemizer_hi.bin", "sourceSha256": "dcee3272f96d7f1b7cc40c5df23060b502a5b9066f7cb20092413dff82a487f5", "path": "phonemizers/hi/phonemizer_hi.onnx", "sizeBytes": 9205753, "sha256": "7e046cd695d2615bad723b24e7fbe0339594526f6953df4c5d20aa53862a9678"},
+    {"language": "it", "sourcePath": "phonemizers/it/phonemizer_it.bin", "sourceSha256": "dca8d068d76134a40856cd874ea6e5e05c988914369ab643f52ab77a512067e3", "path": "phonemizers/it/phonemizer_it.onnx", "sizeBytes": 7105527, "sha256": "30c115355c28c1c8657eba91a1557d89b9bb69b373202399546719cf2991f9f8"},
+    {"language": "pt", "sourcePath": "phonemizers/pt-br/phonemizer_pt.bin", "sourceSha256": "89049ea03c52ffa7233a343d44a35059aae3b1231d772c8c498fbc4427756ecf", "path": "phonemizers/pt-br/phonemizer_pt.onnx", "sizeBytes": 7105527, "sha256": "fb30ed5fbdf2465b5f3d8a08903d2cc50dfa77b4c4c24518ac0ba26640393f52"},
+    {"language": "pl", "sourcePath": "phonemizers/pl/phonemizer_pl.bin", "sourceSha256": "ec85f4dc2c4ac7a72ff88b98b0664a4ed887bd15c0d5add2eb1d6a6ee05b73f2", "path": "phonemizers/pl/phonemizer_pl.onnx", "sizeBytes": 7105527, "sha256": "4cdbafd810ed3cad701c24380894115f848cfa39602d731e7a8e085adee62233"},
+    {"language": "de", "sourcePath": "phonemizers/de/phonemizer_de.bin", "sourceSha256": "4888dc7e54dc66098551555096562063364091fc246da0d057b629587bedaa0b", "path": "phonemizers/de/phonemizer_de.onnx", "sizeBytes": 7105527, "sha256": "aef1d8a6163b426733059f35f406c540ccd08a3f7855eebe6a09ab4908d5dac7"}
+  ]
+}

validation/package-validation.json

@@ -1,5 +1,5 @@
 {
-  "catalogVersion": "2.0.0",
+  "catalogVersion": "2.1.0",
   "catalogSchemaValidated": true,
   "onnxRuntimeVersion": "1.29.0",
   "artifactsVerified": 183,
@@ -7,6 +7,18 @@
   "languageProfilesValidated": 11,
   "voicesValidated": 159,
   "frontendCasesValidated": 12,
+  "frontendOnnxModelsValidated": 9,
+  "frontendOnnxSmokeTests": [
+    {"language": "en-us", "path": "phonemizers/en-us/phonemizer_en_us.onnx", "sha256": "479cd9d89819a60c4f8609dbb116ae5b362d46c0c592b97605968cbaef1e7bc6", "logitsShape": [1, 2, 116]},
+    {"language": "en-gb", "path": "phonemizers/en-gb/phonemizer_en_gb.onnx", "sha256": "065baba624db8391905e53c78706a12c5f4cba12a77e62a90900b2113bdb17e7", "logitsShape": [1, 2, 116]},
+    {"language": "es", "path": "phonemizers/es/phonemizer_es.onnx", "sha256": "0437232bb50cffdefc51995dc8195c14992b185655e3bc0f0005b97a7f162240", "logitsShape": [1, 2, 116]},
+    {"language": "fr", "path": "phonemizers/fr/phonemizer_fr.onnx", "sha256": "d0ca22d75569827f86d73bd8f071a128e478d4f6f107e94035236ba080658485", "logitsShape": [1, 2, 116]},
+    {"language": "hi", "path": "phonemizers/hi/phonemizer_hi.onnx", "sha256": "7e046cd695d2615bad723b24e7fbe0339594526f6953df4c5d20aa53862a9678", "logitsShape": [1, 2, 116]},
+    {"language": "it", "path": "phonemizers/it/phonemizer_it.onnx", "sha256": "30c115355c28c1c8657eba91a1557d89b9bb69b373202399546719cf2991f9f8", "logitsShape": [1, 2, 116]},
+    {"language": "pt", "path": "phonemizers/pt-br/phonemizer_pt.onnx", "sha256": "fb30ed5fbdf2465b5f3d8a08903d2cc50dfa77b4c4c24518ac0ba26640393f52", "logitsShape": [1, 2, 116]},
+    {"language": "pl", "path": "phonemizers/pl/phonemizer_pl.onnx", "sha256": "4cdbafd810ed3cad701c24380894115f848cfa39602d731e7a8e085adee62233", "logitsShape": [1, 2, 116]},
+    {"language": "de", "path": "phonemizers/de/phonemizer_de.onnx", "sha256": "aef1d8a6163b426733059f35f406c540ccd08a3f7855eebe6a09ab4908d5dac7", "logitsShape": [1, 2, 116]}
+  ],
   "cases": [
     {
       "id": "en-us-af-heart",