Yeah, the model is small enough that inference is already basically instant for ... | Hacker News

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

salamo 53 days ago | parent | context | favorite | on: Speech Recognition and TTS in less than 500kb

Yeah, the model is small enough that inference is already basically instant for my usecase (only 6 transformer layers for the blog search).

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