Instructions to use Phoonnx/outetts-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OuteTTS
How to use Phoonnx/outetts-1B with OuteTTS:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
outetts-1B
A OuteTTS model by OuteAI, from OuteAI/Llama-OuteTTS-1.0-1B, packaged for phoonnx, our ONNX text-to-speech library.
Model details
| Architecture | OuteTTS |
| Upstream | OuteAI/Llama-OuteTTS-1.0-1B |
| Author | OuteAI |
| Languages | ar-SA, be-BY, bn-BD, fa-IR, lt-LT, pt-PT, sw-KE, ta-IN, uk-UA |
| Text input | Unicode codepoints of the text |
How to use
pip install --pre phoonnx
import wave
from phoonnx.model_manager import TTSModelManager
manager = TTSModelManager()
manager.load()
manager.merge_default_voices()
voice = manager.voices["outetts/1B/ar"].load()
with wave.open("output.wav", "wb") as wav_file:
text = "..." # a sentence in ar-SA
voice.synthesize_wav(text, wav_file)
In OVOS, phoonnx installs the ovos-tts-plugin-phoonnx plugin. Select the voice in mycroft.conf:
{"tts": {"module": "ovos-tts-plugin-phoonnx", "ovos-tts-plugin-phoonnx": {"voice": "outetts/1B/ar"}}}
Text front end
phoonnx hands the text to scriptconv, our text conversion library, which normalises it and turns it into the model's input:
unicode:UnicodeCodepointPhonemizerfromscriptconv.phonemizers.base, in scriptconv itself.
phoonnx voices
outetts/1B/aroutetts/1B/beoutetts/1B/bnoutetts/1B/faoutetts/1B/ltoutetts/1B/ptoutetts/1B/swoutetts/1B/taoutetts/1B/uk
Licence
The upstream declares the licence cc-by-nc-sa-4.0 in the model card of OuteAI/Llama-OuteTTS-1.0-1B.
The licence notes for this model:
|
1B/model.onnx(+model.onnx_data) | re-exported by phoonnx from OuteAI/Llama-OuteTTS-1.0-1B - see below | CC-BY-NC-SA-4.0 (non-commercial) | |1B/tokenizer.json| OuteAI/Llama-OuteTTS-1.0-1B-ONNX | CC-BY-NC-SA-4.0 (non-commercial) | languages; phoonnx resolves those 14 to it. The 1B is CC-BY-NC-SA-4.0 - **not licensed Ukrainian. Check the 1B license before you deploy it.
- 1B (CC-BY-NC-SA-4.0), 23 trained languages: the 14 above plus Arabic, Belarusian,
Related projects
- phoonnx: runs this model, in Python and in OVOS.
- scriptconv: text normalisation, script conversion and phonemizers for phoonnx.
- The OuteTTS collection: every OuteTTS model packaged for phoonnx.
- Downloads last month
- 32