---
title: "Phonon-2.5 vs NVIDIA Canary"
description: "Canary-1B-v2 covers Phonon-2.5's 25 languages and translates; Phonon-2.5 has lower English word error (5.06 % vs 5.81 %). Canary-Qwen 2.5B scores 4.55 %."
canonical: "https://www.fermionresearch.com/models/phonon-2-5/vs-canary/"
source: "Fermion Research"
---

Phonon/facts checked 13 November 2026

# Phonon-2.5 vs NVIDIA Canary

NVIDIA's Canary family spans an English-only 2.5B model and a 25-language 1B model. Here is how each compares with Phonon-2.5 on English, languages, size and where they run.

[Phonon-2.5 downloads and benchmarks](https://www.fermionresearch.com/models/phonon-2-5/)

## The short answer

Canary-1B-v2 covers exactly the same 25 European languages as Phonon-2.5 and adds speech translation to and from English; Phonon-2.5 has the lower English word error (5.06 % against 5.81 % on the Open ASR Leaderboard's seven sets) from 156 MB against 3,916 MB. For English alone, Canary-Qwen 2.5B is lower than both Phonon models (4.55 % against 4.82 % for Phonon-2.5 English).

Choose Canary for translation, for the lowest English word error in an NVIDIA GPU stack, or if you already run NeMo. Choose Phonon-2.5 for the same 25 languages with no GPU and a twenty-fifth of the download.

## Side by side

Canary facts from NVIDIA's model cards on Hugging Face, read 2026-11-13. Sizes from the leaderboard snapshot.

|  | Phonon-2.5 | Canary-1B-v2 | Canary-Qwen 2.5B |
| --- | --- | --- | --- |
| Model type | Open weights on Hugging Face | Open weights | Open weights |
| Size | 156 MB download (Phonon-2.5 English: 158 MB) | 978 M parameters, 3,916 MB | 2.5 B parameters, 5,000 MB |
| Languages | 25 European languages (Phonon-2.5 English: English only) | The same 25 European languages | English |
| English word error, seven Open ASR sets | 5.06 % (Phonon-2.5 English: 4.82 %) | 5.81 % | 4.55 % |
| Price | No per-hour fee when self-hosted | Free to run; no hosted price checked | Free to run; no hosted price checked |
| Where it runs | Your hardware: CPUs (Linux x86-64 and arm64, Windows x86-64), Apple silicon, NVIDIA GPUs, Android | NVIDIA GPUs on Linux with NeMo | NVIDIA GPUs with NeMo (Linux, Windows) |
| Streaming | Yes, live WebSocket from fermion serve | Not mentioned on the card | Not mentioned on the card |
| Speech translation | No | English to 24 languages and 24 to English | No (LLM mode answers questions about the transcript) |
| Word timestamps | Yes (--json output) | Word and segment level | Not mentioned on the card |

## English, set by set

Canary-Qwen 2.5B is lower than Phonon-2.5 on six sets; Phonon-2.5 English is lower on Earnings-22 and VoxPopuli. Canary-1B-v2 is lower than Phonon-2.5 on LibriSpeech other and SPGISpeech and higher on the rest. Two smaller English Canary models are also in the snapshot: Canary-1B-Flash at 5.03 % (3,244 MB) and Canary-180M-Flash at 5.69 % (737 MB).

| Test set | Phonon-2.5 | Phonon-2.5 English | Canary-1B-v2 | Canary-Qwen 2.5B | Canary-1B-Flash | Canary-180M-Flash |
| --- | --- | --- | --- | --- | --- | --- |
| LibriSpeech clean | 1.60 | 1.64 | 1.76 | 1.23 | 1.20 | 1.52 |
| LibriSpeech other | 3.41 | 3.56 | 3.07 | 2.63 | 2.52 | 3.42 |
| AMI | 9.12 | 8.76 | 13.03 | 7.91 | 10.58 | 12.09 |
| Earnings-22 | 6.72 | 6.22 | 7.28 | 6.41 | 6.79 | 8.33 |
| GigaSpeech | 8.04 | 7.99 | 9.12 | 7.80 | 8.19 | 8.87 |
| SPGISpeech | 3.31 | 3.31 | 2.03 | 1.70 | 1.75 | 2.04 |
| VoxPopuli | 3.23 | 2.28 | 4.39 | 4.14 | 4.17 | 3.57 |
| Average of the seven | 5.06 | 4.82 | 5.81 | 4.55 | 5.03 | 5.69 |

## The 25 languages

Canary-1B-v2's card reports 8.40 % word error on FLEURS across its 25 languages, measured without punctuation and capitalisation. Phonon-2.5's 11.71 % FLEURS average comes from our own scoring code, and we have not scored Canary-1B-v2 with it, so the two figures should not be set against each other. If one language matters most, test both on your own audio in that language.

## Where each is the better choice

- Canary: speech translation in 48 directions, English accuracy with Canary-Qwen 2.5B, an LLM mode that summarises or answers questions about a transcript, and NeMo pipelines on NVIDIA GPUs.
- Phonon-2.5: the same 25 languages from 156 MB, CPUs, Apple silicon and Android with no GPU, lower English word error than Canary-1B-v2, and a ready server with file and streaming routes.

```text
pip install fermion-research
fermion transcribe phonon-2.5 interview.wav --json
fermion serve phonon-2.5   # POST /v1/audio/transcriptions, GET /v1/audio/stream
```

## Questions

## Related

- [Phonon-2.5 vs Parakeet](https://www.fermionresearch.com/models/phonon-2-5/vs-parakeet/)
- [FLEURS results, 25 languages](https://www.fermionresearch.com/speech/fleurs-results-25-languages/)
- [Phonon-2.5 vs Qwen3-ASR](https://www.fermionresearch.com/models/phonon-2-5/vs-qwen3-asr/)
- [The Open ASR Leaderboard and Phonon](https://www.fermionresearch.com/models/phonon-2-5/open-asr-leaderboard/)

## Sources and method

- Canary-1B-v2 languages, translation, timestamps, runtime and FLEURS figure: huggingface.co/nvidia/canary-1b-v2, read 2026-11-13.
- Canary-Qwen 2.5B parameters, language, modes and runtime: huggingface.co/nvidia/canary-qwen-2.5b, read 2026-11-13.
- Rival English word error: Open ASR Leaderboard, seven English sets, snapshot 2026-09-25 (huggingface.co/spaces/hf-audio/open_asr_leaderboard). Sizes from the same snapshot.
- Phonon-2.5 and Phonon-2.5 English: Fermion Research measurement, Phonon-2.5 release post (2026-10-22), Open ASR Leaderboard scoring code, full test sets of the same seven sets.
- Phonon-2.5 FLEURS average: Phonon-2.5 release post, full FLEURS test sets, our scoring code.

Canonical: https://www.fermionresearch.com/models/phonon-2-5/vs-canary/

Source: [https://www.fermionresearch.com/models/phonon-2-5/vs-canary/](https://www.fermionresearch.com/models/phonon-2-5/vs-canary/)
