How to use from the
Use from the
Transformers library
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-to-speech", model="openlimi/Vosen-tts-tiny")
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("openlimi/Vosen-tts-tiny", device_map="auto")
Quick Links

πŸŽ™οΈ Vosen-TTS-Tiny: Lightweight Uzbek Text-to-Speech (Experimental 31M)

Hugging Face Model License: OpenRAIL-M Language: Uzbek

Vosen-TTS-Tiny is an ultra-lightweight, fully trained Text-to-Speech (TTS) model tailored exclusively for the Uzbek language.

⚠️ MUHIM ESLATMA / IMPORTANT NOTE: Ushbu model ishlab chiqarish va yakuniy mahsulotlar (production) uchun mo'ljallanmagan. Sifat ko'rsatkichlari mukammal darajada emasligi sababli, loyiha sof ilmiy-tajriba va tadqiqot (experimental/research) maqsadida yuklandi. This model is purely experimental and not recommended for production environments due to average synthesis quality.


πŸ“Š Model Specifications

  • Architecture: Specialized Phonon architecture adapted for Uzbek phonemes.
  • Parameters: 31 Million (Extremely lightweight & blazing fast on CPU/GPU).
  • Training Regime: Fully trained from scratch (Full Train) specifically on Uzbek speech data.
  • Target Audience: Researchers, hobbyists, and developers studying low-resource Uzbek speech synthesis.

🌐 SEO Keywords & Search Optimization

This model is heavily indexed and optimized for search terms including: Uzbek TTS, O'zbekcha matnni nutqqa o'tkazish, Uzbek Speech Synthesis, Vosen TTS Tiny, 31M Uzbek TTS model, Sun'iy intellekt ovoz o'zbekcha, Phonon Uzbek, OpenLimi Vosen Tiny, Lightweight speech synthesis Uzbek.


πŸ“„ License & Attribution

This model is released under the CreativeML OpenRAIL-M license. You are free to use and build upon this model for personal and research applications.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support