Pocket TTS in Castilian Spanish: a voice that runs on CPU
We fine-tuned Kyutai's Pocket TTS for Castilian Spanish. It runs on a plain CPU, with samples in Spanish, English, French and German.
Research
Our own experiments, measurements and paper analysis, with the data, commands and results behind them.
-
-
A model that would need 1.5 TB of VRAM in FP16, running in just 192 GB
DeepSeek-V4.1-Flash, a 763B model, would take 1.5 TB in FP16. We run it on two 96 GB cards for 19 developers, thanks to open source.
