runFullImpl: failed to generate timestamp token - skipping one second while using ggml-large-v3_2

[awaqawaqawaq]

runFullImpl: failed to generate timestamp token - skipping one second while using ggml-large-v3_2 but there is no problems when i use ggml-large-v2 and i also want to ask why cant i use ggml-large-v3-q5_0.bin

[leixuexin]

the same problem

[datan79]

yup exact same problem

[EinProfispieler]

same here

[emcodem]

solution here: https://github.com/Const-me/Whisper/issues/188

[ThisIsLoui]

solution here: #188

It dosen't work. And the same error exists when using ggml-medium. I think it was caused by a high sampling rate of the target video.

[jwlrxy]

i cant use v3 model. is it not supported by this?

[ThisIsLoui]

i cant use v3 model. is it not supported by this?

You can try the custom version made by @emcodem, which can be found in this issue: #188 (see the fourth comment)

[thisanickname]

same

[PandaBear1314]

same here