This is an 8-bit quantized version of the Celtia model from the Proxecto Nós https://huggingface.co/proxectonos/Nos_TTS-celtia-vits-graphemes
This model has been optimized to offer a significant reduction in size and memory usage, making it ideal for deployment on devices with limited resources, while maintaining high-quality audio synthesis.
Key Features
Model: Celtia (VITS-based)
Original Source: Nos_TTS-celtia-vits-graphemes https://huggingface.co/proxectonos/Nos_TTS-celtia-vits-graphemes
Optimization: INT8 quantization
Language: Galician
Function: Text-to-Speech (TTS)