Whisper: Nvidia RTX 4090 vs. M1 Pro with MLX

Re:Whisper: Nvidia RTX 4090 vs. M1 Pro with MLX by LiamMcCalloway on Wednesday December 13, 2023 @11:28AM (#38629706)

I'll take this opportunity to ask for help: What's a good open source transcription and diarization app or work flow?

I looked at https://github.com/thomasmol/cog-whisper-diarization and https://about.transcribee.net/ (from the people behind Audapolis) but neither work that well -- crashes, etc.

Thank you!

[ Parent | on HN ]

Re:Whisper: Nvidia RTX 4090 vs. M1 Pro with MLX by dvfjsdhgfv on Wednesday December 13, 2023 @11:37AM (#38629849)

I developed my own solutions, pretty rudimentary - it divides the MP3s into chunks that Whisper is able to handle and then sends them one by one to the API to transcribe. Works as expected so far, it's just a couple of lines of Python code.

[ Parent | on HN ]

Re:Whisper: Nvidia RTX 4090 vs. M1 Pro with MLX by mosselman on Wednesday December 13, 2023 @04:45PM (#38634584)

I would like to know the same.

It shouldn’t be so hard since many apps have this. But what is the most reliable way right now?

[ Parent | on HN ]