TheTwelveYearOld@lemmy.world to Linux@lemmy.worldEnglish · 2 days agoFFmpeg 8.0 merges OpenAI "Whisper Filter" for automatic speech recognition, Vulkan AV1 encoding, & VP9 decodingwww.phoronix.comexternal-linkmessage-square7linkfedilinkarrow-up152arrow-down10file-textcross-posted to: linux@lemmy.mllinux@programming.devopensource@programming.dev
arrow-up152arrow-down1external-linkFFmpeg 8.0 merges OpenAI "Whisper Filter" for automatic speech recognition, Vulkan AV1 encoding, & VP9 decodingwww.phoronix.comTheTwelveYearOld@lemmy.world to Linux@lemmy.worldEnglish · 2 days agomessage-square7linkfedilinkfile-textcross-posted to: linux@lemmy.mllinux@programming.devopensource@programming.dev
https://www.phoronix.com/news/FFmpeg-Vulkan-AV1-Encoding https://www.phoronix.com/news/FFmpeg-Lands-Whisper
minus-squareMysteriousSophon21@lemmy.worldlinkfedilinkEnglisharrow-up2·2 days agoWhisper struggles with non-english languages and background noise - you might get better results using the larger models (medium/large) with a lower temperature setting to reduce the hallucinations and repetitions your experiencing.
minus-squareinfjarchninja@lemmy.mllinkfedilinkEnglisharrow-up1·22 hours agohey MysteriousSophon21 I did use the larger and medium models with Open whisper and Fast whisper. I did not consider the lower termperature settings Thank you
Whisper struggles with non-english languages and background noise - you might get better results using the larger models (medium/large) with a lower temperature setting to reduce the hallucinations and repetitions your experiencing.
hey MysteriousSophon21
I did use the larger and medium models with Open whisper and Fast whisper.
I did not consider the lower termperature settings
Thank you