Is the Whisper model better than say Youtube's auto transcribing? I hope it is because the one on YT gets so much wrong it's almost comical.
Show HN: Self-host Whisper As a Service with GUI and queueing
11–20 of 60 posts
Re: Show HN: Self-host Whisper As a Service with GUI and queueing
#12Is the Whisper model better than say Youtube's auto transcribing? I hope it is because the one on YT gets so much wrong it's almost comical.
It is pretty good. I tried it a few times and there were minor mistakes at best. The Whisper readme itself shows a live transcription use case.
Re: Show HN: Self-host Whisper As a Service with GUI and queueing
#13By the way there is also another project called Whisper.cpp: https://github.com/ggerganov/whisper.cpp Which uses x8 less memory than the Python implementation for the tiny model. It would be a good idea to keep an eye on it since there are Python bindings planned on the roadmap: https://github.com/ggerganov/whisper.cpp#bindings
And there's a fork of that that uses DirectCompute to run it on GPUs without Cuda on Windows:
Re: Show HN: Self-host Whisper As a Service with GUI and queueing
#14People interested in this might also be interested in transcribe-anything [1]. It automates video fetching and uses whisper to generate .srt, .vtt and .txt files. [1] https://github.com/zackees/transcribe-anything
This have the same output formats plus it's own Jojo-format to open in an atm internal Mac-app and in the editor-feature-branch.
Re: Show HN: Self-host Whisper As a Service with GUI and queueing
#15Is the Whisper model better than say Youtube's auto transcribing? I hope it is because the one on YT gets so much wrong it's almost comical.
But more impressive is that it understand a lot of other languages then just English. Really impressed with hard-to-understand Norwegian dialects.
Re: Show HN: Self-host Whisper As a Service with GUI and queueing
#16The only thing Whisper misses is speaker diarization. I'm currently working on a model that uses Whisper + pyannote to transcribe Interviews and also detects who is speaking. It's working but damn it takes so long
Ok. Our service is pretty fast. Also the M-Macs is really fast imo
Re: Show HN: Self-host Whisper As a Service with GUI and queueing
#17Is the Whisper model better than say Youtube's auto transcribing? I hope it is because the one on YT gets so much wrong it's almost comical.
We use whisper at $dayjob and we found that it is far better than Azures transcripts and we found that Azure and GCP had about the same correctness.
I'd assume whisper will be better than YT auto ones for sure, especially if you choose the right model
Re: Show HN: Self-host Whisper As a Service with GUI and queueing
#18The only thing Whisper misses is speaker diarization. I'm currently working on a model that uses Whisper + pyannote to transcribe Interviews and also detects who is speaking. It's working but damn it takes so long
I'm badly looking for that! Is there a repo I can follow?
Re: Show HN: Self-host Whisper As a Service with GUI and queueing
#19The only thing Whisper misses is speaker diarization. I'm currently working on a model that uses Whisper + pyannote to transcribe Interviews and also detects who is speaking. It's working but damn it takes so long
I'm badly looking for that! Is there a repo I can follow?
not GP (hoping he responds tho) but i've been collecting a couple of diarization options: https://github.com/sw-yx/ai-notes/blob/main/AUDIO.md
basically whisper.cpp has some support but its not great (based on my own testing)
- https://huggingface.co/spaces/vumichien/whisper-speaker-diar...
- https://github.com/Majdoddin/nlp pyannote diarization
- whisperX with diarization https://twitter.com/maxhbain/status/1619698716914622466 https://github.com/m-bain/whisperX
Re: Show HN: Self-host Whisper As a Service with GUI and queueing
#20By the way there is also another project called Whisper.cpp: https://github.com/ggerganov/whisper.cpp Which uses x8 less memory than the Python implementation for the tiny model. It would be a good idea to keep an eye on it since there are Python bindings planned on the roadmap: https://github.com/ggerganov/whisper.cpp#bindings
Is there a fork running it on Apple's Neural Engine?