@whitewhoadie: 🚨 NVIDIA JUST DROPPED A 0.6B CPU-ONLY SPEECH RECOGNITION MODEL Nemotron-3.5-ASR delivers real-time streaming ASR across 40+ languages — and it runs entirely on CPU. Ships with: • Only 0.6B parameters • Real-time streaming output • 2.5x faster than official Nemo runtime (same accuracy) • Fully offline capable • Easy integration into local agent pipelines Another strong small model for on-device/local AI stacks. 👉 https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b Who’s running local speech recognition today? Drop a 🔥

WHOADIE

Open In TikTok:

Region: US

Thursday 18 June 2026 17:48:44 GMT

33669

1503

193

Music

Download

No Watermark .mp4 (1.26MB) No Watermark(HD) .mp4 (0.89MB) Watermark .mp4 (1.2MB) Music .mp3

Comments

WhyteNation :

600 million params. now called 0.6 billion or 0.0006 trillion parameters

2026-06-19 00:18:27

Hack Daddy :

I can't keep.up

2026-06-18 23:22:22

The CCSI :

i like piper

2026-06-18 23:31:21

drenmorina23 :

Can you tell me more about this

2026-06-18 17:55:12

⎝⎝✧𝙅ᥲ𝙨ѻп✧⎠⎠ :

but pleas 0.6b is not more tahn 2 gb its fit in almost all newer gpu so wahts the point of it to be slower

2026-06-18 18:29:27

Nahom :

Why not just use whisper

2026-06-18 21:27:08

~/appricorn :

Doesn't matter

2026-06-18 22:32:19

wesjofficial :

If we can run it locally this could be a missing piece to the puzzle 😁

2026-06-18 18:50:21

iimmppoossiibbllee :

any demo video?

2026-06-18 21:52:27

ur_wife :

but the hiccups only in studio mode with sengiser recording mic and in english

2026-06-18 19:49:49

iCreatr :

It’s slow

2026-06-19 04:35:45

To see more videos from user @whitewhoadie, please go to the Tikwm homepage.