YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

MeloTTS to ONNX Exporter

A script to convert MeloTTS models to ONNX format for use with sherpa-onnx.

Supported Languages

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.

Quick Start

# Install dependencies and export a model (default: ko)
./run.sh ko

# Export a specific language
./run.sh fr

Manual Usage

pip install -r requirements.txt
python -m unidic download  # required for Japanese

python export-onnx.py --language zh

Options

python 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)

Output Files

onnx_exports/<lang>/
β”œβ”€β”€ model.onnx      # ONNX model with embedded metadata
β”œβ”€β”€ tokens.txt      # Phoneme symbol β†’ index mapping
β”œβ”€β”€ lexicon.txt     # Word β†’ phoneme + tone mapping
└── metadata.json   # Model metadata (language_code, sample_rate, speakers, …)

lexicon.txt format

word  phone1 phone2 ...  tone1 tone2 ...

Chinese and English models include English words for mixed-language pronunciation. Monolingual models (ja, fr, es, ko) contain only target language vocabulary.

How It Works

The export script wraps the MeloTTS SynthesizerTrn model in a ModelWrapper that:

  1. Accepts token IDs, tone information, speaker ID, and synthesis parameters
  2. Sets BERT embeddings to zeros (C++ BERT inference is not available in sherpa-onnx)
  3. Calls the internal VITS inference and exports via torch.onnx.export

Note: BERT embeddings are zeroed out, so voice quality may differ slightly from the original PyTorch model.

License

MeloTTS is licensed under MIT. See MeloTTS for details.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support