Daniel Bevenius
Daniel Bevenius
> [@danbev](https://github.com/danbev) Can you reproduce on your end? I'll take a look 👍 I've only been testing with the sample jfk.wav which is pretty short.
@ggerganov I've tried with various files like `gb0.ogg`, `gb1.ogg`, `mm1.wav` but they all complete. Could you share the file you are using so I can try the exact same one?...
Thanks, I've tried these but I've not been able to reproduce yet. I'll continue transcribing and see when I run into it. > Eventually it hangs. I also reproduce it...
@slaren @ggerganov Thanks for the reviews/feedback! I've updated with a commit containing your suggestions as I understood them. Would it makes sense to follow up this PR with one that...
Can you try this without using the `--jinja` flag when starting the server?
> Is there anyway to use both functionality with the OpenAI compatible chat completion API? I think this might be a bug and I'm looking into this. If we take...
@tulang3587 Sorry but I think I might have mislead you, and the "fix" I proposed above does not seem to be correct. However there is an open [PR](https://github.com/ggml-org/llama.cpp/pull/11900) which mentions...
@foldl Sorry about the delay on this. Would you be able rebase this and resolve conflicts here and we should be able to merge this.
I believe this pr has been superseded by https://github.com/ggerganov/whisper.cpp/commit/206459a80477f00799b383d4c7e81d207c95d00b. Please feel free to reopen if there is anything missing in the current implementation
This is being worked on alongside of https://github.com/ggerganov/llama.cpp/pull/11292.