StyleTTS2 UA Denys

--- license: mit language: - uk pipeline_tag: text-to-speech tags: - text-to-speech - tts - styletts2 - ukrainian - onnx base_model: patriotyk/styletts2_ukrainian_multispeaker --- # StyleTTS2 Ukrainian (multispeaker) — ONNX export An ONNX export of **[patriotyk/styletts2_ukrainian_multispeaker](https://huggingface.co/patriotyk/styletts2_ukrainian_multispeaker)** for on-device inference (ONNX Runtime, e.g. iOS). This repository adds **no new training** — it is a faithful export of patriotyk's PyTorch weights, plus a small graph fix so the model loads in ONNX Runtime. All credit for the model, training data, and Ukrainian front-end belongs to **[@patriotyk](https://huggingface.co/patriotyk)**. Please cite and support the original work. ## Source - **Model:** [patriotyk/styletts2_ukrainian_multispeaker](https://huggingface.co/patriotyk/styletts2_ukrainian_multispeaker) - **Inference / export code:** [patriotyk/styletts2-inference](https://github.com/patriotyk/styletts2-inference) - **Front-end (stress + IPA):** [patriotyk/ukrainian-word-stress](https://github.com/patriotyk/ukrainian-word-stress), [patriotyk/ipa-uk](https://github.com/patriotyk/ipa-uk) - **Demo:** [patriotyk/styletts2-ukrainian](https://huggingface.co/spaces/patriotyk/styletts2-ukrainian) ## What was changed 1. Exported the PyTorch model to ONNX with `torch.onnx.export` (opset 19), using patriotyk's own `export_onnx.py` procedure. 2. Applied the one required graph fix: a `Transpose` node whose `perm` contained `-1` (which ONNX Runtime rejects) was rewritten to `2`. This is the same patch patriotyk's export script applies. **The file here is already patched** — no post-processing is needed to load it in ORT. ## Files | file | description | |------|-------------| | `model.onnx` | the exported + patched model (330 MB) | | `config.yml` | model config (vocab, params) — from the source repo | | `style_denys.pt` / `style_denys.bin` | the "Денис Денисенко" speaker style vector (`s_prev`, 256 float32), as `torch` tensor and raw little-endian floats | ## Inputs / outputs | name | type | shape | |------|------|-------| | `tokens` | int64 | `[seq_length]` | | `speed` | float32 | scalar | | `s_prev` | float32 | `[1, 256]` (a speaker style vector) | | `output_wav` | float32 | `[seq_length]` — 24 kHz mono PCM | Tokens are produced by patriotyk's front-end (`ukrainian-word-stress` → `ipa-uk`...