Skip to content

Questions about ASR/STT #151

Answered by A-n-d-r-e-a-s-M
A-n-d-r-e-a-s-M asked this question in Q&A
Questions about ASR/STT #151
@A-n-d-r-e-a-s-M A-n-d-r-e-a-s-M
May 3, 2024 · 1 comment
Answered by A-n-d-r-e-a-s-M Return to top
Discussion options

A-n-d-r-e-a-s-M
May 3, 2024

You must be logged in to vote
Answered by A-n-d-r-e-a-s-M May 13, 2024

I believe you used an RTX 3090 in this test and you used ct2-transformers-converter to create tovera/wis-whisper... models? Then it can be defined with which quantization the models will be loaded.

View full answer

Replies: 1 comment

Comment options

A-n-d-r-e-a-s-M
May 13, 2024
Author

You must be logged in to vote
0 replies
Answer selected by A-n-d-r-e-a-s-M
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
1 participant
@A-n-d-r-e-a-s-M