Inference Optimization Voice AI Open Models

NVIDIA NeMo Parakeet

Fast, accurate automatic speech recognition models.

A family of NVIDIA NeMo automatic speech recognition models for transcribing spoken audio to text, including Parakeet TDT variants.

Model Intelligence

Benchmarkable

Model level

family

Recent stories

1 linked story

releaseSECONDARY2026-09-21

Parakeet Redux cuts NVIDIA's Parakeet from 1.2 GB to 178 MB

Parakeet Redux compresses NVIDIA's Parakeet from 1.2 GB to 178 MB with ternary weights. Its author reports 113× real-time CPU speed and stronger results on the 25-language FLEURS benchmark.