Founders
826 subscribers
312 photos
30 videos
1 file
127 links
Download Telegram
gm
๐Ÿฅฐ13๐Ÿ”ฅ4โค3
๐Ÿ˜15๐Ÿคฃ4
Last weekend we won a big Lllama 3 Hackaton!

We built a smart glasses from scratch using off-the-shelf parts in $20 and it runs entirely on Open Source networks.

This kind of blown up everywhere - now everyone knows what we have done and we have 1500+ of preorders in the first day. Gizmodo took small interview, virtually anyone i am talking two knows about our glasses. I have built firmware and base app (everything up to LLM) and guys benchmarked different llms and picked the best approach.

What we found is that Moondream v2 + Llama 3 is capable to run similar to what OpenAI demonstrated. It can sense what's happening around, answering questions. You can get faster than realtime responses via Groq API for Llama 70B, TTS is also quite fast. STT is also 100x of realtime. Ofc openai is much better at this, but hacked in the weekend solution also works.

My goal getting street creds in bay area is slowly working!
๐Ÿ”ฅ15๐Ÿฆ„5โค4
Got Google Glass Enterprise 2 for prototyping of OpenGlass!

Google discounted them year ago, but a lot of vendors has them in stock and therefore cost is now ~$250 with fancy italian frame. Before they were like $1500 for google part only.

And they run fully unlocked android!
๐Ÿ”ฅ11โค1
My first audio pre-training finished!

Thankfully my small cluster of 4090 finished pre-training of my audio foundational model! It took about 30 days to finish. This model is akin to original GPT (not chat one) in essence that it is not really that useful without finetuning, but you can finetnue it to do denoising, speech enhancement, speaker separation, text-to-speech tasks. All this tasks are very very important for AI Wearables and every single company i have talked too are struggling with it.
๐Ÿ‘6๐Ÿค”3๐Ÿ’…2๐Ÿ‘จโ€๐Ÿ’ป1
gn
๐Ÿ”ฅ4๐Ÿ•Š2๐Ÿซก1
Me, when i can't find what i can't build or what to learn.

Any recommendations?
๐Ÿ”ฅ1
This media is not supported in your browser
VIEW IN TELEGRAM
SuperVoice Enhance

My new model for speech enhance and denoising. This model processes noisy or damaged audio extracts high quality voice. Should work with most languages out of the box.

Model and sources: https://github.com/ex3ndr/supervoice-enhance
๐Ÿ”ฅ14โค2
I guess this is pride month on my bench ๐Ÿณ๏ธโ€๐ŸŒˆ
Please open Telegram to view this post
VIEW IN TELEGRAM
๐Ÿฆ„8๐Ÿ˜4โค1๐Ÿคฎ1๐Ÿฅด1๐Ÿ’Š1๐Ÿ‘พ1
gm
๐Ÿฅฐ10โค6๐Ÿ”ฅ3๐Ÿ˜2
gm๐ŸŽ๏ธ
โค16๐Ÿ“7๐Ÿ”ฅ4๐Ÿ™ˆ4
gm
๐Ÿ”ฅ14โคโ€๐Ÿ”ฅ3โค2โšก1๐Ÿ‘1๐Ÿ“1
Someone need to stop me
๐Ÿ”ฅ3๐Ÿ˜ฑ2
๐Ÿ˜8๐Ÿค”2
gm
โค8๐Ÿฅฐ3โœ2
Worst feature - it has been year or so and it is still super distractive!
๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿคฃ๐Ÿคฃ๐Ÿคฃ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡บ๐Ÿ‡ธ
Please open Telegram to view this post
VIEW IN TELEGRAM
๐Ÿ˜13๐Ÿ”ฅ3