speech recognition

canary-180m-flash

Small multilingual multitask Canary Flash model for speech recognition and translation, with experimental word timestamps.

NVIDIAUSA

Levelmodel

Classspeech recognition

Parameters182M

Contextnot in the notes

Released11 Mar 2025

Opennessopen weights permissive

Runs onnot in the notes

Statusactive

R&D Topics

Massively multilingual speech recognitionproduced by Speech-to-speech translationproduced by

Identity

Developer: NVIDIA
Family: not in the notes
Released: 11 Mar 2025 sourcesregistry date
Weights published: –
Record checked: 12 Oct 2026

Where this comes from

Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture: other FastConformer encoder with Transformer decoder
Total parameters: 182M sources
Active parameters: –
Checkpoint parameters: –
Note: 182 million parameters per the card.
Context length: not in the notes
Input: audio
Output: text

Where this comes from

Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness: open weights permissive
Licence: Creative Commons Attribution 4.0 sources
Access routes: open weights download

Where this comes from

The licence file governs over registry tags and aggregator labels.

Deployment

Runs on: not in the notes
Footprint: not in the notes
Runtimes: not in the notes

Where this comes from

Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support: not stated
Regional languages: not in the notes
Jakarta hosting: unknown
Languages: English, German, French, Spanish

Where this comes from

Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Links

Developer

NVIDIAbig tech, USA

Model

canary-180m-flashNVIDIA, speech recognition

R&D TopicsMassively Multilingual Speech Recognition Speech-to-Speech Translation

Use Casesnone recorded

Who Runs Itnone recorded

Graph

Organisations 1

NVIDIAbig tech, USADeveloper

R&D topics 2

Massively Multilingual Speech RecognitionTraining one speech recognition model on hundreds of thousands of hours or hundreds of la…produced bySpeech-to-Speech TranslationTranslating spoken language directly into speech or text in another language, in one mode…produced by

Sources

huggingface.co/nvidia/canary-180m-flash https://huggingface.co/nvidia/canary-180m-flash

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Canary-180m-Flash", https://aurion.semai.id/models/nvidia-canary-180m-flash/, records of October 2026.