The website you link being timesofisrael is a bit ironic. Great app nonetheless! If they're writing about it then it's working and is among the most probable reasons of the tiktok ban
Diabolo96
joined 1 year ago
Will it help improve wine? If yes, great! If no, I geuss it's a great learning tool for new OS devs.
every app they ever released is completely missing from my library, they're even missing from my purchasing history.
Somewhat unrelated but :
why didn't they mention that anywhere
Perhaps it Happened too fast to react, or maybe they didn't really care. It's Likely the latter.
wouldn't their website also be shut down as well?
Not really. Hosting a website cost pennies and they probably want to keep the domain name.
Maybe they closed down and had to remove everything due to copyright problems/sales weren't worth having to do costumer services or something like that.
I bet it's not that uncommon either. Just yesterday, I remembered a game I saw years ago called 'green project' that was in early access at the time and wanted to check it out. so I went to look for it but it was gone despite the game still being sold on steam and being on version 1.4.2, but the last update was on 2022.
Last update 2020. I think the playstore delete games that don't get any updates for some time. Just get the apk from an alternative store if you know what I mean.
I was hoping for something that I could use on a mobile app.
Record then transcribe later ? But you can try https://whisper.ggerganov.com ( this runs on your browser but nothing is sent. So works even on your Android/IOS phone.) the website owner is a trusted dev that made whisper.cpp and llama.ccp, the latter basically being the backbone of the entire LLM industry.
I'm not sure what "adapting the model size" means so this might be more complicated than I'm looking for.
A bit of complexity is generally the price to pay for freedom from the constant surveillance and data gathering. Plus, It's actually super easy. Bigger model means better transcription quality, but the smaller ones are really good already. The base.en is probably all you need anyway.
On pc, you can generally try any app from github. They basically all use the same backend.
I found a few : https://whishper.net/ https://github.com/chidiwilliams/buzz
No. Quantization make it go faster. Not blazing fast, but decent.
Completely forgot to tell you to only use quantized models. Your pc can run 4bit quantized versions of the models I mentioned. That's the key for running llms on at consumer level hardware. You can later read further about the different quantizations and toy with other ones like Q5_K_M and such.
Just read phi-3 got released and apparently it's a 4B that reach gpt 3.5 level. Follow the news and wait for it to be add to ollama/llama.ccp
Thank you so much for taking the time to help me with that! I'm very new to the whole LLM things, and sorta figuring it out as I go
I became fascinated with llms after the first AI booms but all this knowledge is basically useless where I live, so might as well make it useful by teaching people what i know.
The key is quantized models. A full model wouldn't fit but a 4bit 8b llama3 would fit.
Damn, so it's been discussed for years but nothing happened. Israel commit atrocities (like always ) but unlike it's other domestic media, the US government and some of its billionaires can't censor, lie and push their narrative anymore, so the youth finally see the truth about the genocidal apartheid, ethno-state that is Israel. Now, they ban tiktok.
This is just another perspective you haven't thought about, or don't want to think about because of it's morbid implications about your country (if you're from USA)