I've found that for CPU inference the PyTorch-based (non-quantized) version of P... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

mscdex 40 days ago | parent | context | favorite | on: Local, CPU-Friendly, High-Quality TTS (Text-to-Spe...

I've found that for CPU inference the PyTorch-based (non-quantized) version of Pocket TTS actually performs (both speed and quality-wise) better than the ONNX version, even after fiddling with all of the knobs that ONNX provides.

teravor 40 days ago [–]

i found the exact opposite, the pytorch version on the cpu barely does over 2 times realtime while i can get the onnx int8 version to reach 5x.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact