Publish reproducible OpenVoice package metadata

README.md

@@ -0,0 +1,66 @@
+---
+license: mit
+language:
+- zh
+pipeline_tag: text-to-speech
+library_name: onnxruntime
+tags:
+- openvoice
+- melotts
+- onnx
+- xrtranslate
+base_model:
+- myshell-ai/MeloTTS-Chinese
+---
+
+# XRTranslate OpenVoice ONNX
+
+Community-maintained, reproducible ONNX conversions of official MyShell MeloTTS
+language checkpoints for XRTranslate's pure-Rust OpenVoice V2 provider. These
+are not official MyShell or NVIDIA artifacts.
+
+## Packages
+
+| Package | Language | Precision | Installed size | Base output |
+| --- | --- | --- | ---: | ---: |
+| `openvoice-v2-zh-onnx-fp16` | Chinese (mixed English) | FP16 | 446.8 MiB | 44,100 Hz |
+
+Each package is self-contained: its language-specific frontend and feature
+graph, MeloTTS acoustic graph, OpenVoice V2 converter, reference speaker
+encoder, source tone embedding, licenses, and a machine-readable per-file
+SHA-256 manifest. XRTranslate returns converted audio at 22,050 Hz mono PCM16.
+
+## Reproducibility
+
+The production graphs are exported in the existing `torch211cu128` Conda
+environment with Python 3.10, PyTorch `2.11.0+cu128`, CUDA 12.8, ONNX 1.22.0,
+ONNX Runtime 1.23.2, and opset 16. PyTorch is not upgraded or downgraded.
+
+```powershell
+conda run -n torch211cu128 python third_party/openvoice_onnx_export/build.py `
+  --language <language-key> `
+  --output runtime/.temp/openvoice-onnx-export
+```
+
+Exact upstream commits, source hashes, graph tensor contracts, conversion
+versions, smoke-test results, and produced file hashes are recorded in each
+`packages/<language-key>/v1/package-manifest.json`.
+
+## Upstream and licenses
+
+- [MeloTTS](https://github.com/myshell-ai/MeloTTS) and
+  [OpenVoice](https://github.com/myshell-ai/OpenVoice) are MIT licensed.
+- Each package manifest pins its exact MeloTTS checkpoint repository and commit.
+- Source tone embeddings come from
+  [`myshell-ai/OpenVoiceV2`](https://huggingface.co/myshell-ai/OpenVoiceV2).
+- Language-specific BERT/tokenizer, G2P, dictionary, and normalization notices
+  are preserved inside that package.
+
+See each package's `licenses/` directory before redistribution.
+
+## Limitations
+
+The packages require a compatible CUDA ONNX Runtime in XRTranslate. They are
+not standalone Python TTS APIs. Voice cloning transfers tone color;
+pronunciation, accent, and prosody remain controlled by the selected MeloTTS
+language pack.