# NVIDIA Releases Canary 1B v2 Multilingual Speech Model

> The new 1-billion-parameter model handles both transcription and translation across five languages using the company's efficient FastConformer architecture.

Published by The Open Weights on Aug 4, 2025. Canonical: https://theopenweights.com/news/canary-1b-v2-9jie

## Key facts

- Company: NVIDIA
- Model: Canary 1B v2
- Version: v2
- Category: Speech → Text
- Modalities: Speech → Text
- License: CC BY 4.0 (Fully open, commercial use allowed)
- Parameters: 1B
- Architecture: CanaryForConditionalGeneration
- Precision: FP32
- Weights size: 3.9 GB
- Languages: 25 languages
- Significance: notable
- Published: 2025-08-04
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/nvidia/canary-1b-v2
- Canonical URL: https://theopenweights.com/news/canary-1b-v2-9jie

NVIDIA has released Canary 1B v2, a versatile 1-billion-parameter model for automatic speech recognition (ASR) and translation. Published with a permissive CC-BY-4.0 license, the model provides developers with a powerful new tool for building voice-enabled applications.

The model is built on NVIDIA's FastConformer architecture, which is designed for high-performance and efficient speech processing. Canary excels at multilingual tasks, handling both transcription in a source language and translation from that language into English within a single model.

## Core Capabilities

According to its official release card, Canary 1B v2 was trained to handle several key tasks without the need for separate models:
*   **Transcription:** Supports English, German, French, Spanish, and Mandarin.
*   **Translation:** Can translate any of the supported source languages into English text.
*   **Formatting:** Includes automatic punctuation and capitalization to produce more readable output.

This release adds another high-quality, open-source option to a field largely defined by models like OpenAI's Whisper. By providing a permissively licensed and efficient alternative, NVIDIA gives developers more flexibility for integrating advanced speech AI. The model and its usage instructions are available on [NVIDIA's Hugging Face page](https://huggingface.co/nvidia/canary-1b-v2).

## Get the model

- [Hugging Face](https://huggingface.co/nvidia/canary-1b-v2)

## Sources

- [nvidia/canary-1b-v2](https://huggingface.co/nvidia/canary-1b-v2) — Hugging Face, Aug 4, 2025

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "NVIDIA Releases Canary 1B v2 Multilingual Speech Model", The Open Weights, Aug 4, 2025, https://theopenweights.com/news/canary-1b-v2-9jie