--- license: apache-2.0 language: - ru pipeline_tag: text-to-speech datasets: - egnch/tiny-voca-ru-dataset tags: - text-to-speech - tts - russian - onnx - safetensors - lightweight - tiny-voca --- # tiny-voca-ru A Russian adaptation of the 4.5M-parameter [`tiny-voca`](https://github.com/n4ze3m/tiny-voca) text-to-speech model with female and male voices, trained from scratch on [`egnch/tiny-voca-ru-dataset`](https://huggingface.co/datasets/egnch/tiny-voca-ru-dataset). - **Demo:** https://huggingface.co/spaces/egnch/tiny-voca-ru-demo - **Dataset:** https://huggingface.co/datasets/egnch/tiny-voca-ru-dataset - **Code:** https://github.com/yilbegan/tiny-voca-ru - **PyPI:** https://pypi.org/project/tiny-voca-ru/ | Property | Value | | --- | --- | | Parameters | 4,534,411 (~18.2 MB `safetensors`, ~21.4 MB `ONNX`) | | Voices | `F` (female), `M` (male) | | Output | 24 kHz mono | | Frontend | Pure-Python Russian normalizer, stress (`lite` / `full`), 61-symbol IPA | | Weights | `model.safetensors` + `config.json`, `onnx/model.onnx` + `onnx/model.json`, `onnx/omograph.onnx` | | CPU Speed (4 threads) | 115× real-time (PyTorch), 81× real-time (ONNX Runtime) | | License | Apache-2.0 (bundled `ruaccent` stress data: MIT) | ## Audio Samples | Voice | Text | Audio | | --- | --- | --- | | `F` | Здравствуйте! Это tiny-voca-ru, маленькая модель синтеза речи на русском языке. | | | `M` | Здравствуйте! Это tiny-voca-ru, маленькая модель синтеза речи на русском языке. | | | `F` | Встречу перенесли на 15:30, 14 марта, так что у нас осталось около 45 минут. Билет стоит 1250 рублей. | | | `M` | Ты правда думал, что я забуду про твой день рождения? Конечно, нет! | | ## Usage ### Installation ```bash # ONNX Runtime inference (no PyTorch) pip install "tiny-voca-ru[onnx]" # PyTorch + safetensors pip install "tiny-voca-ru[torch]" ``` ### Python API ```python from tiny_voca_ru import Synthesizer synth = Synthesizer.from_pretrained("egnch/tiny-voca-ru") # ONNX Runtime backend # synth = Synthesizer.from_pretrained("egnch/tiny-voca-ru", backend="onnx") result = synth.save_wav( "Здравствуйте! Встречу перенесли на 15:30, 14 марта.", "hello.wav", voice="M", # "F" or "M" speed=1.0, # 0.25 .. 4.0 pitch_shift=0.0, # log-F0 offset (0.058 ≈ +1 semitone) pitch_range=1.0, # 0.0 .. 3.0 stress="lite", # "lite" | "full" | "none" ) ``` ### CLI ```bash tiny-voca-ru-speak --voice F --text "Привет! Билет стоит 1250 рублей." --output out.wav ``` Pass `--backend onnx` to use ONNX Runtime. Manual stress can be marked with `+` before the stressed vowel (`зам+ок`). ## Changes from `tiny-voca` Follows the [`tiny-voca`](https://github.com/n4ze3m/tiny-voca) architecture and training recipe, adapted for Russian: - **Phoneme inventory:** 61-symbol Russian IPA set (5 special, 12 punctuation, 36 consonants with palatalization pairs, 8 vowels including reduced `ɐ` and `ə`). - **Frontend (`tiny_voca_ru.frontend`):** Pure-Python Russian text normalization, stress placement (`lite` via bundled `stress.txt.gz` + `accent.onnx`, or `full` via 10 MB INT8 `onnx/omograph.onnx`), and rule-based G2P. - **Training:** Trained from scratch for 104,000 steps (4.9 h on 1× NVIDIA L40S) on 18,517 aligned clips (21.96 h) from [`egnch/tiny-voca-ru-dataset`](https://huggingface.co/datasets/egnch/tiny-voca-ru-dataset), using `facebook/wav2vec2-lv-60-espeak-cv-ft` CTC durations during data preparation. Custom-voice fine-tuning scripts (`tiny-voca-ru-prepare`, `tiny-voca-ru-train`) are available in the [GitHub repository](https://github.com/yilbegan/tiny-voca-ru). ## Evaluation Evaluated at 104k steps with the default `lite` frontend against the Qwen3-TTS teacher on the test split (696 clips, Whisper `large-v3-turbo` ASR). CPU speed measured on AMD Ryzen 5 3600X (4 threads, 55.03 s of audio). | Metric | Split | tiny-voca-ru | Teacher | | --- | --- | --- | --- | | CER | test (696 clips) | 0.46% (`F` 0.43%, `M` 0.49%) | 0.31% | | WER | test (696 clips) | 2.03% | 1.54% | | Stress accuracy (CTC top-1) | test dict words (3,905) | 98.5% | 95.6% | | Homographs (`lite` / `ruaccent turbo3.1` ref) | homographs (250) | 56.0% / 91.6% | — | | Numbers ASR exact match | test numeric templates (139) | 90.6% | 92.1% | | Speed (PyTorch / ONNX CPU, 4 threads) | 55.03 s audio | 115× / 81× RT | — | | Speed (ONNX Runtime Web, WASM 1 thread) | Chromium | 16.7–21.7× RT | — | ## Limitations - Russian only; two voices (`F`, `M`) inheriting Qwen3-TTS pronunciation traits. - Default `lite` stress does not disambiguate context-dependent homographs; use `stress="full"` (10 MB INT8 `onnx/omograph.onnx`) or explicit `+` marks. - Rule-based numeral case inflection and Latin transliteration can occasionally err on complex syntax or foreign names. ## Citation ```bibtex @misc{chetvertkov2026tinyvocaru, author = {Chetvertkov, Evgeniy}, title = {tiny-voca-ru: A 4.5M-Parameter Russian Text-to-Speech Model}, year = {2026}, url = {https://huggingface.co/egnch/tiny-voca-ru}, note = {ORCID: https://orcid.org/0009-0006-6158-2624} } ``` If you use this model, please also cite the original [`tiny-voca`](https://huggingface.co/n4ze3m/tiny-voca): ```bibtex @software{nazeem2026tinyvoca, author = {Nazeem, Muhammed}, title = {tiny-voca: a 4.5M-parameter two-voice English text-to-speech model}, year = {2026}, url = {https://huggingface.co/n4ze3m/tiny-voca} } ``` ## License & Attribution - **Code & weights:** Apache-2.0 ([LICENSE](LICENSE), [NOTICE](NOTICE)). - **Stress dictionary, `accent.onnx`, and INT8 `omograph.onnx` (`tiny2.1`):** [ruaccent](https://github.com/Den4ikAI/ruaccent) (MIT). - **Dataset:** [`egnch/tiny-voca-ru-dataset`](https://huggingface.co/datasets/egnch/tiny-voca-ru-dataset) (CC BY 4.0). - **Acknowledgements:** [`tiny-voca`](https://github.com/n4ze3m/tiny-voca) (Apache-2.0), alignment calibration inspired by [słyszę głosy](https://github.com/damaon/slyszeglosy) (Apache-2.0), Qwen3-TTS (Apache-2.0).