@Walaa_Almalki9 أ. ولاء، اشتغلت على نظام تصنيف ذكاء اصطناعي لوزارة العدل. لو يفيدك أشارك تجربتي عن تطبيقات الذكاء الاصطناعي في المجال القانوني، تواصلي معي 🙏
LFM2.5-Audio-1.5B
> Real-time text-to-speech and ASR
> Running locally on a CPU with llama.cpp
> Interleave speech and text
It's super elegant, I'm bullish on local audio models
NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents.
Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms.
This agent actually uses *three* NVIDIA open source models:
- Nemotron Speech ASR
- Nemotron 3 Nano 30GB in a 4-bit quant (released in December)
- A preview checkpoint of the upcoming Magpie text-to-speech model
These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.)
The code for this agent is open source too, of course. You can deploy it to production with @modal and @pipecat_ai cloud, or run locally on an @nvidia DGX Spark or RTX 5090.
Mathematician Terence Tao:
Training and running LLMs isn't mathematically difficult; any math undergrad could understand the basics
The mystery is that we have no theory to predict why models excel at certain tasks and fail at others
"we can only make empirical experiments"
I am not promoting these here, but seriously I have learnt a lot from these 3 here. For Solo Builders these are gold 🤑💸
1. Alex West's books on building - must read
2. Tony Dinh's My Indie Book - covers A to Z
3. Make by Pieter Levels - classic start
links below 👇