Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
StevenWaterman
on Sept 21, 2022
|
parent
|
context
|
favorite
| on:
Whisper – open source speech recognition by OpenAI
Was this with the `base` model? `large` is running ok on a P100 in colab, but is about 4% the speed of `base.en`. Certainly seems like some of these models will be fast enough for real-time.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
