Instructions to use nipsterx93/simrig-voices with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Pocket-TTS
How to use nipsterx93/simrig-voices with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("nipsterx93/simrig-voices") voice_state = tts_model.get_state_for_audio_prompt( "hf://kyutai/tts-voices/alba-mackenna/casual.wav" ) audio = tts_model.generate_audio(voice_state, "Hello world, this is a test.") # Audio is a 1D torch tensor containing PCM data. scipy.io.wavfile.write("output.wav", tts_model.sample_rate, audio.numpy()) - Notebooks
- Google Colab
- Kaggle
SimRIG voices for Pocket TTS
Voice states for Kyutai Pocket TTS, used by the SimRIG Remastered
plugin for SimHub. One file per voice and per language model: <language>/<voice>.safetensors, for the models of
kyutai/pocket-tts-without-voice-cloning
(italian, english, german, french, spanish). Any voice can speak any of the five languages, with its own accent.
| Voice | Source recording | Licence |
|---|---|---|
vctk_p256 |
VCTK corpus, speaker p256 (CSTR, University of Edinburgh) | CC BY 4.0 |
erick |
voice donation | CC0 1.0 |
enrique |
voice donation | CC0 1.0 |
2181 |
voice donation | CC0 1.0 |
3973 |
voice donation | CC0 1.0 |
vctk_p256 is derived from the CSTR VCTK Corpus (Yamagishi, Veaux, MacDonald, University of Edinburgh), licensed
CC BY 4.0. The voice states were made with Pocket TTS by Kyutai; the Pocket TTS models are licensed CC BY 4.0.
- Downloads last month
- -