Comment on WhisperX — Automated Transcripts w/ Timestamps and Speaker Tagging
wise_pancake@lemmy.ca 1 week ago
That is cool! I’ve been wanting I’ve wanted to use a model like this but haven’t really looked.
Are you self hosting the long context llm, of do what are you using?
Context lengths are what kill a lot of my local llm experiments.
dgdft@lemmy.world 1 week ago
I did a lot of my exploration back when GPT4 128K over API was the only long-context game in town.
I imagine the options are much better these days between Llama 3/4, Deepseek, and Gemini, and Qwen — but haven’t tried them locally myself.