OuteTTS
Collection
OuteTTS models in ONNX for phoonnx. โข 3 items โข Updated
How to use Phoonnx/outetts-0.6B 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
A OuteTTS model by OuteAI, from OuteAI/OuteTTS-1.0-0.6B, packaged for phoonnx, our ONNX text-to-speech library.
| Architecture | OuteTTS |
| Upstream | OuteAI/OuteTTS-1.0-0.6B |
| ONNX conversion | OuteAI/OuteTTS-1.0-0.6B-ONNX |
| Author | OuteAI |
| Languages | de-DE, en-US, es-ES, fr-FR, hu-HU, it-IT, ja-JP, ka-GE, ko-KR, lv-LV, nl-NL, pl-PL, ru-RU, zh-CN |
| Text input | Unicode codepoints of the text |
pip install --pre phoonnx
import wave
from phoonnx.model_manager import TTSModelManager
manager = TTSModelManager()
manager.load()
manager.merge_default_voices()
voice = manager.voices["outetts/0.6B/de"].load()
with wave.open("output.wav", "wb") as wav_file:
text = "..." # a sentence in de-DE
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/0.6B/de"}}}
phoonnx hands the text to scriptconv, our text conversion library, which normalises it and turns it into the model's input:
unicode: UnicodeCodepointPhonemizer from scriptconv.phonemizers.base, in scriptconv itself.outetts/0.6B/deoutetts/0.6B/enoutetts/0.6B/esoutetts/0.6B/froutetts/0.6B/huoutetts/0.6B/itoutetts/0.6B/jaoutetts/0.6B/kaoutetts/0.6B/kooutetts/0.6B/lvoutetts/0.6B/nloutetts/0.6B/ploutetts/0.6B/ruoutetts/0.6B/zhThe upstream declares the licence apache-2.0 in the model card of OuteAI/OuteTTS-1.0-0.6B.
The licence notes for this model:
|
0.6B/model.onnx(+model.onnx_data),0.6B/tokenizer.json| OuteAI/OuteTTS-1.0-0.6B-ONNX | Apache-2.0 | The two model sizes carry different licenses. The 0.6B is Apache-2.0 and covers 14
- 0.6B (Apache-2.0), 14 trained languages: English, Chinese, Dutch, French,