Insanely Fast Whisper API Deployable to Fly GPU

Posted by indigodaddy on Tuesday May 28, 2024 @06:31PM
from the github.com dept.

( 4 comments | 3 points | on HN )

Re:Insanely Fast Whisper API Deployable to Fly GPU by 2Gkashmiri on Tuesday May 28, 2024 @11:20PM (#40508092)

Is there a commercially available whisper api or you have to use it locally only ?

[ Parent | on HN ]

Re:Insanely Fast Whisper API Deployable to Fly GPU by waldrews on Wednesday May 29, 2024 @04:33AM (#40509750)

OpenAI's speech to text API is the official Whisper implementation. It's expensive.

Many small providers will host Whisper as an endpoint (Replicate for example).

Groq has Whisper in a private beta; if they open it up for commercial usage, cheap and fast, that'll be a game changer.

[ Parent | on HN ]

Re:Insanely Fast Whisper API Deployable to Fly GPU by arthurdelerue on Wednesday May 29, 2024 @08:55AM (#40511472)

NLP Cloud is a good example of a smaller provider that proposes a good Whisper implementation (no downtimes and relatively cheap): https://nlpcloud.com/nlp-automatic-speech-recognition-speech...

[ Parent | on HN ]

Re:Insanely Fast Whisper API Deployable to Fly GPU by brianjking on Wednesday May 29, 2024 @09:43AM (#40511931)

Beautiful, would love a way to deploy this easily on Huggingface Inference Endpoints.

The need for a custom handler.py has always stopped me from doing so.

[ Parent | on HN ]