bobqianic

OpenAI's Whisper currently only handles Any-to-English translations. If you're interested in Any-to-Any translations, you might want to check out Meta's latest Seamless-M4T. 

Hi @slaren , is there a way to completely turn off OpenCL during runtime? Thanks!

>python3 whisper.cpp/models/convert-h5-to-ggml.py distil-medium.en/ whisper.cpp/ some-output-folder/ Replace `whisper.cpp/` with the path to the OpenAI Whisper repository. See https://github.com/ggerganov/whisper.cpp/discussions/1414#discussioncomment-7461216

Which language have you selected? The default is English.

Indeed, I've noticed that as well. I'll need some time to look into it more thoroughly.

> After some tests, I achieved a 4x reduction in WER in faster-whisper by setting without_timestamps=True That's really interesting. Have you experimented with OpenAI's official implementation of Whisper? It also...

Give my latest PR #1768 a try. It's still a WIP, but if you compile it yourself, it should significantly reduce the hallucinations towards the end of the audio file.

> @bobqianic I'm trying this new build now and maybe it is better at the end, but I still see many hallucinations when there are long completely silent gaps in...

> @ggerganov any schedules to implement [#1838 Skip silence around hallucinations](https://github.com/openai/whisper/pull/1838)? https://github.com/ggerganov/whisper.cpp/pull/1768#issuecomment-1924743917

> Hey guys. I had a good time today benchmarking and comparing different inference backends on the transcription of 3000 Brazilian Portuguese audio files of varying quality. While I had...