Just released Parakeet Redux!
This is a AI post classified by Jev as Voice AI (a model release), kept by the AI Radar because it carries real work, not commentary.
Just released Parakeet Redux! A ternary speech-to-text model, built by compressing NVIDIA's Parakeet model from 1.2GB to 178MB. Runs at 113x realtime on CPU, and beats the base model on the 25-language FLEURS benchmark while staying within 0.3 WER on English.
Posted by vik (29.2k followers) 1 h ago · 442 likes · 10.1k views · view the original post on X. Kept by the AI Radar as Voice AI.
More AI work like this
- BREAKING: Freya TTS Adam v1 by @FreyaVoice takes the #1 spot on AudioRealismBench with… — @DesignArena
- VOICE AGENTS HAVE A TRANSCRIPT PROBLEM — @DataChaz
- We just added Grok Voice Transcribe 2.0 to Aerivoice! — @imnotchalk
- A little experiment into the compression of ASR models for some later ideas. The QAD… — @DJLougen
- Day after voice calls, Grok Bot can send voice notes. I talk live when I’m in it — then… — @MichaelGannotti
- NetEase-Youdao releases Confucius4-R2T2, a true-streaming ASR model for live captions,… — @ModelScope2022
- NVIDIA research papers are on fire recently! — @omarsar0
- New model: qwen-audio-3.1-realtime-plus — @aitrackerbot
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 39.3k posts from 5k X accounts over the last 14 days, 1.6k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 17:06 UTC. Full method.