161–170 of 232 posts
Earlier quoted context omitted.
aws s3 sync + image snapshot
all that costs time :-/ When you're finished working, you got to wait for the syncs to finish (or I guess run them all the time?). For home computer setups, you can simply walk away when you need a break.
This looks huge. Anyone know how this compares with Whisper in terms of quality and speed?
according to their blog post[1], MMS achieves ~half the error rate on words, while supporting 11x more languages. pretty impressive. [1] https://ai.facebook.com/blog/multilingual-model-speech-recog...
Earlier quoted context omitted.
You "spend hours messing around" with everything you don't know or understand at first. One could say the same about writing the software itself. At its core Dockerfiles are just shell scripts with worse syntax, so it's not really that much more to learn. Once you get it done once, you don't have to screw around with it anymore, and you have it on any box you want in seconds. In either case you have to spend hours sc…
I'm having trouble imagining what data I would store in a database as opposed to a filesystem if my goal is to experiment with large models like Stable Diffusion.
Earlier quoted context omitted.
You can finetune whisper, stable diffusion, and LLM up to about 15B parameters with 24GB VRAM. Which leads you to what hardware to get. Best bang for the $ right now is definitely a used 3090 at ~$700. If you want more than 24GB vram just rent the hardware as it will be cheaper. If you're not willing to drop $700 don't buy anything just rent. I have had decent luck with vast.ai
There is the world of used Nvidia Teslas, like the M40. Very cheap, but some assembly required.
Why is Meta open sourcing their AI work like this? Is it because they don't have a great reputation even among tech companies?
Meta has had a culture of open source, even before their reputation got bad (React, RocksDB, Thrift, folly, etc). They open source a lot of their AI models (instead of just source) because they don't have an enterprise cloud to sell these things, unlike Amazon/Google/Microsoft's offerings (which all offer speech transcription and text to speech as services).
Earlier quoted context omitted.
I wonder what the performance is on English specifically. Edit: Just checked the paper, it seems to be worse[1][2] but feel free to correct me. I feel like they should've just taken the Whipser architecture, scaled it, and scaled the dataset as they did. [1] Page: https://i.imgur.com/bq15Tno.png [2] Paper: https://scontent.fcai19-5.fna.fbcdn.net/v/t39.8562-6/3488279...
It's worse on English and a lot of other common languages (see Appendix C of the paper). It does better on less common languages like Latvian or Tajik, though.
Earlier quoted context omitted.
There is the world of used Nvidia Teslas, like the M40. Very cheap, but some assembly required.
What do you mean by assembly needed? I looked them up and they look like normal gfx cards. Am I missing something?
Real Open AI lab.
Imagine if we used these types of models for like 500 years and it locked their vocabulary in time, disallowing any further language blending; then somehow the servers turned off and nobody could communicate across language barriers anymore. Someone should write that down in some sort of short-story involving a really tall structure.