Re:Writeout.ai – Transcribe and translate any audio files. F...
by rolisz on Wednesday March 08, 2023 @01:14PM
(#35072606)
On a 1080Ti (so a 6 year old GPU), the large model runs in 1x time (so transcribing 10 minutes takes 10 minutes) and I've successfully transcribed even 1h+ files.
[ Parent
| on HN ]
Re:Writeout.ai – Transcribe and translate any audio files. F...
by kkielhofner on Wednesday March 08, 2023 @05:01PM
(#35075344)
FWIF an optimized implementation I've been working on comes in at roughly 70x realtime (large-v2, beam size 5) on an RTX 3090.
Re:Writeout.ai – Transcribe and translate any audio files. F...
by rolisz on Thursday March 09, 2023 @01:49AM
(#35078851)
Nice! Are you going to release it publicly?
Re:Writeout.ai – Transcribe and translate any audio files. F...
by kkielhofner on Thursday March 09, 2023 @05:23PM
(#35087671)
Great question!
We're still very early stage and stealth so it's not quite clear to us where our lines are with regards to special sauce/significant competitive advantage.
As the CTO (and lead dev) I'd lean towards open sourcing it (because it's awesome and we're standing on the shoulders of open source giants already) but it may become clear it's too differentiating to open source. As I said it's just too early to tell.
What I can say is if we open source it HN will be the first to hear about it!