| Code | Language | Speakers | Lexicon source |
|---|---|---|---|
| zh | Chinese | 1 | pypinyin dict + CMU English |
| en | English | 5 | CMU eng_dict |
| en_v2 | English (v2) | 4 | CMU eng_dict |
| en_newest | English (v3) | 1 | CMU eng_dict |
| ja | Japanese | 1 | wordfreq top-10000 + MeCab/unidic |
| fr | French | 1 | wordfreq top-10000 + melo g2p |
| es | Spanish | 1 | wordfreq top-10000 + gruut |
| ko | Korean | 1 | wordfreq top-10000 + hangul jamo |
Note: English (en, en_v2, en_newest) and Chinese (zh) models include English words in their lexicon for mixed-language support. Monolingual models (ja, fr, es, ko) do not include English words.
1# Install dependencies and export a model (default: ko)
2./run.sh ko
3
4# Export a specific language
5./run.sh fr1pip install -r requirements.txt
2python -m unidic download # required for Japanese
3
4python export-onnx.py --language zhpython export-onnx.py --language <LANG> [options]
--language zh | en | en_v2 | en_newest | ja | fr | es | ko (default: ko)
--output Output directory (default: ./onnx_exports/<LANG>/)
--device cpu | cuda (default: auto-detect)
--opset ONNX opset version (default: 18)onnx_exports/<lang>/
├── model.onnx # ONNX model with embedded metadata
├── tokens.txt # Phoneme symbol → index mapping
├── lexicon.txt # Word → phoneme + tone mapping
└── metadata.json # Model metadata (language_code, sample_rate, speakers, …)word phone1 phone2 ... tone1 tone2 ...SynthesizerTrn model in a ModelWrapper that:torch.onnx.exportNote: BERT embeddings are zeroed out, so voice quality may differ slightly from the original PyTorch model.