# NVIDIA Releases 600M Parakeet for Speech Recognition

> The new FastConformer model uses a specialized training technique to improve transcription accuracy in noisy, real-world environments.

Published by The Open Weights on Aug 4, 2025. Canonical: https://theopenweights.com/news/parakeet-tdt-0-6b-v3-p9bm

## Key facts

- Company: NVIDIA
- Model: Parakeet TDT 0.6B v3
- Version: v3
- Category: Speech → Text
- Modalities: Speech → Text
- License: CC BY 4.0 (Fully open, commercial use allowed)
- Parameters: 600M
- Architecture: ParakeetForTDT
- Precision: FP32
- Weights size: 2.5 GB
- Languages: 25 languages
- Significance: notable
- Published: 2025-08-04
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3
- Canonical URL: https://theopenweights.com/news/parakeet-tdt-0-6b-v3-p9bm

NVIDIA has released a new open model for automatic speech recognition (ASR) called Parakeet TDT 0.6B. As part of its NeMo toolkit for conversational AI, this 600-million-parameter model is designed to transcribe speech across multiple languages with high accuracy.

The model's architecture and training method are key to its performance. It uses a FastConformer encoder, which is known for its efficiency in processing audio sequences. The "TDT" in its name signifies Transducer with Denoising Training, a technique that makes the model more robust by training it to ignore noise and focus on the primary speech signal, a common challenge in real-world applications.

This release provides developers with a powerful and relatively lightweight tool for building speech-enabled products. With a permissive CC-BY-4.0 license, Parakeet can be freely used and modified for both research and commercial projects. Its 0.6-billion-parameter size makes it more accessible to deploy than the massive, multi-billion-parameter systems that often dominate ASR research.

By open-sourcing a specialized model like Parakeet, NVIDIA is contributing a significant building block to the conversational AI ecosystem. Developers interested in experimenting with the model can find the weights and usage instructions on the [official Hugging Face repository](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3).

## Get the model

- [Hugging Face](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3)

## Sources

- [nvidia/parakeet-tdt-0.6b-v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) — Hugging Face, Aug 4, 2025

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "NVIDIA Releases 600M Parakeet for Speech Recognition", The Open Weights, Aug 4, 2025, https://theopenweights.com/news/parakeet-tdt-0-6b-v3-p9bm