Reexport models for RNET v0.10.0

README.md

@@ -21,7 +21,7 @@ It can perform speech synthesis in 8 different languages, including fine-tuned P
 
 The models support **input shape dynamism** and cover the input range of `1` up to `128` tokens.
 
-Additionally, the repository contains essential resources for **G2P (grapheme-to-phoneme)** preprocessing (see **v0.9.0** branch) required by the Kokoro model,
+Additionally, the repository contains essential resources for **G2P (grapheme-to-phoneme)** preprocessing required by the Kokoro model,
 including simple word-by-word phonemization models (also in ExecuTorch format).
 
 If you'd like to run these models in your own ExecuTorch runtime, refer to the 
@@ -39,8 +39,34 @@ make sure your runtime is compatible with the ExecuTorch version used to export
 
 ## Repository Structure
 
-The repository contains 3 main directories:
+```
+.
+├── config.json              # Backend-agnostic model manifest
+├── phonemizer/              # G2P data files + per-language phonemizer models
+├── voices/                  # Pre-computed speaker embeddings
+└── xnnpack/                 # XNNPACK-exported .pte files, one directory per model variant
+    ├── standard/
+    │   ├── config.json
+    │   ├── duration_predictor_std_xnnpack_fp32.pte
+    │   └── synthesizer_std_xnnpack_fp32.pte
+    ├── german/
+    │   ├── config.json
+    │   ├── duration_predictor_de_xnnpack_fp32.pte
+    │   └── synthesizer_de_xnnpack_fp32.pte
+    └── polish/
+        ├── config.json
+        ├── duration_predictor_pl_xnnpack_fp32.pte
+        └── synthesizer_pl_xnnpack_fp32.pte
+```
+
 - `phonemizer` - data files required by the [Phonemis](https://github.com/IgorSwat/Phonemis) package - responsible for input preprocessing part
   of React Native ExecuTorch Kokoro pipeline.
 - `voices` - a collection of pre-computed speaker embeddings used by the Kokoro model to synthesize speech with specific vocal characteristics.
-- `xnnpack` - exported, XNNPACK-optimized Kokoro runtime modules.
+- `xnnpack` - exported, XNNPACK-optimized Kokoro runtime modules. Each variant directory ships a `config.json` manifest
+  describing its `.pte` files and their method signatures.
+
+Each variant is composed of two sub-models that run sequentially:
+
+1. **Duration predictor** — predicts per-token durations and the prosody features `d`. Exported as a bundled program exposing
+   `forward_32`, `forward_64` and `forward_128`, one method per padded token bucket.
+2. **Synthesizer** — encodes text, predicts F0/N and decodes the waveform. Exported with dynamic shapes behind a single `forward` method.

xnnpack/german/{duration_predictor_de.pte → config.json}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e1fdaf0535ce0179366db37e772c6af4344ab951548004d45db8725d92e5d57
-size 62424392
+oid sha256:bf6eac054d3e9cc94e6f3f2dd5117ae5c95be4221a1d8da301c57f3f01449eb1
+size 4406

xnnpack/{standard/duration_predictor_std.pte → german/duration_predictor_de_xnnpack_fp32.pte}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad1eb2a78e5975a959891c627f9005bc9eee77b6c8275ba3c591e1f526d62e81
-size 62397896
+oid sha256:d745ed3793b68d8c6c7e2189f39bc4fc2ec30b4be9c27eb50648f59470105b87
+size 59307208

xnnpack/german/{synthesizer_de.pte → synthesizer_de_xnnpack_fp32.pte}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57197e4d0142db1c63f9f085504cbfac9f22ece094c94f176150aaddeea3bead
-size 272466032
+oid sha256:14056f50118fa51c027f60cfd74133384d61b80bae5645a7ff10d9b7e5e4b511
+size 272463344

xnnpack/polish/{duration_predictor_pl.pte → config.json}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f639f3cca95688e32028232e743e6058d367f1e14136a7f79d148e6f041bff
-size 62424392
+oid sha256:e802f70b98c8603fce6bdf94bbaf2e6352296e3bd80fe398570095a210d2cfbd
+size 4406

xnnpack/polish/{synthesizer_pl.pte → duration_predictor_pl_xnnpack_fp32.pte}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:932ae00ad6576ac7ee63ce37bb67f5d2a4693e03f005c9055ee35fd7d44eaa36
-size 272466032
+oid sha256:2053f3ac747c606df8655922335d98b00948080575742ce4ade7d06441aa020d
+size 59307208

xnnpack/polish/synthesizer_pl_xnnpack_fp32.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89fba6ec41d774595ba581fd0b8f69401618927728b899cf56823457cec4b95
+size 272463344

xnnpack/standard/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6565d2e208b2e32bcba4441f36e75fe142f76493fd69bf1b929c8245b2d07b0
+size 4409

xnnpack/standard/duration_predictor_std_xnnpack_fp32.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781a6e6de5c13cf2c97c4a486c766c92c107ff8ac99d7ae8e991bfb81d701334
+size 59307208

xnnpack/standard/synthesizer_std.pte

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a1d6dea9b16fc3bb60236f886bb460de7c1bf864cecbb93b8768e917740bf38f
-size 272442224

xnnpack/standard/synthesizer_std_xnnpack_fp32.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4ce2b8dcf396b1bc0125d7dbccadd79a4c3dc104bb8776dbcc85c482bcd000
+size 272463344