loom-ai-org/styletts2-ljspeech-loom

StyleTTS2 (LJSpeech)

yl4579's StyleTTS2 LJSpeech checkpoint, exported for loom.cpp. Takes phoneme ids, not text.

This is a loom.cpp export: a single self-describing GGUF that carries its own graph topologies, tokenizer (if any) and driver script, produced by loom-exporter.

Original model

Exported from yl4579/StyleTTS2-LJSpeech. Weights are unmodified; this repo packages the same parameters into loom.cpp's GGUF format.

License

mit, inherited from the base model above.

Language(s)

en

the HF repo carries no license:/language: tags; MIT per the upstream GitHub repo's LICENSE (github.com/yl4579/StyleTTS2)

Usage

Run it with loom-py -- loom-py-rt on PyPI:

pip install loom-py-rt[hub]

import loom

model = loom.Model.from_pretrained("loom-ai-org/styletts2-ljspeech-loom")
# styletts2-ljspeech takes phoneme ids, not text -- see model.driver_source for the exact driver inputs.
audio = model.infer(tokens=[16, 40, 22, 30, 12, 3], n_steps=4, seed=1234)

model.driver_source prints the exact driver script this GGUF embeds, including a header comment documenting every argument model.infer()/model.generate() accepts for this model.

Files

• styletts2-ljspeech.gguf -- the model, exported with loom-exporter.