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.
pip install fermion-research
fermion transcribe phonon-2.5 interview.wav --json
fermion serve phonon-2.5 # POST /v1/audio/transcriptions, GET /v1/audio/streamQuestions
- Is Phonon-2.5 more accurate than NVIDIA Canary?
- Than Canary-1B-v2 in English, yes: 5.06 % against 5.81 % on the Open ASR Leaderboard's seven sets. Canary-Qwen 2.5B (4.55 %) and Canary-1B-Flash (5.03 %) are lower than Phonon-2.5; Phonon-2.5 English (4.82 %) is lower than Canary-1B-Flash but not Canary-Qwen 2.5B.
- Do Canary-1B-v2 and Phonon-2.5 cover the same languages?
- Yes. NVIDIA's card lists the same 25 European languages Phonon-2.5 covers, from Bulgarian to Ukrainian, including Maltese and Greek.
- Can Phonon-2.5 translate like Canary?
- No. Canary-1B-v2 translates speech from English into 24 languages and from 24 languages into English; Phonon-2.5 only transcribes.
- Does Canary run without an NVIDIA GPU?
- NVIDIA's cards list NVIDIA GPU architectures and the NeMo toolkit. Phonon-2.5 runs on CPUs, Apple silicon, NVIDIA GPUs and Android.
- How much smaller is Phonon-2.5 than Canary?
- Phonon-2.5 is 156 MB. In the leaderboard snapshot Canary-1B-v2 is 3,916 MB, Canary-Qwen 2.5B 5,000 MB and Canary-180M-Flash 737 MB.
Related
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/