---
title: "Phonon-2.5 vs Qwen3-ASR"
description: "Qwen3-ASR 1.7B has lower English word error than Phonon-2.5 (4.43 % vs 5.06 %); Phonon-2.5 beats Qwen3-ASR 0.6B and covers 9 European languages Qwen does not."
canonical: "https://www.fermionresearch.com/models/phonon-2-5/vs-qwen3-asr/"
source: "Fermion Research"
---

Phonon/facts checked 13 November 2026

# Phonon-2.5 vs Qwen3-ASR

Qwen3-ASR covers 30 languages and 22 Chinese dialects from 1.6 to 4.1 GB. Phonon-2.5 covers 25 European languages from 156 MB. Which one fits depends on your languages.

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

## The short answer

Qwen3-ASR 1.7B has the lowest English word error of the three: 4.43 % on the Open ASR Leaderboard's seven sets, against 5.06 % for Phonon-2.5, 4.82 % for Phonon-2.5 English and 5.16 % for Qwen3-ASR 0.6B. Choose Qwen3-ASR for Chinese and its dialects, Asian languages, or top English accuracy with a GPU; choose Phonon-2.5 for the European languages Qwen does not list, or when the model must be small or run without a GPU.

Phonon-2.5 covers nine languages that are not in Qwen3-ASR's list: Ukrainian, Slovak, Bulgarian, Croatian, Estonian, Latvian, Lithuanian, Slovenian and Maltese.

## Side by side

Qwen3-ASR facts from the Qwen model cards on Hugging Face, read 2026-11-13. Sizes from the leaderboard snapshot.

|  | Phonon-2.5 | Qwen3-ASR 1.7B | Qwen3-ASR 0.6B |
| --- | --- | --- | --- |
| Model type | Open weights on Hugging Face | Open weights | Open weights |
| Size | 156 MB download (Phonon-2.5 English: 158 MB) | 4,080 MB | 1,565 MB |
| Languages | 25 European languages (Phonon-2.5 English: English only) | 30 languages plus 22 Chinese dialects and accents | Same as 1.7B |
| English word error, seven Open ASR sets | 5.06 % (Phonon-2.5 English: 4.82 %) | 4.43 % | 5.16 % |
| Hosted price per audio hour | No per-hour fee when self-hosted | $0.027 (DeepInfra) | $0.012 (DeepInfra) |
| Where it runs | Your hardware: CPUs (Linux x86-64 and arm64, Windows x86-64), Apple silicon, NVIDIA GPUs, Android | GPU with vLLM or Transformers | GPU with vLLM or Transformers |
| Streaming | Yes, live WebSocket from fermion serve | Yes, vLLM backend only | Yes, vLLM backend only |
| Diarization | No | No | No |
| Word timestamps | Yes (--json output) | Through a separate forced aligner (11 languages, up to 5 minutes) | Same |

## English, set by set

Qwen3-ASR 1.7B is lower than Phonon-2.5 on all seven sets; Phonon-2.5 English is lower only on VoxPopuli (2.28 % against 2.85 %). Against Qwen3-ASR 0.6B, Phonon-2.5 is lower on LibriSpeech, AMI and Earnings-22 and higher on GigaSpeech, SPGISpeech and VoxPopuli.

| Test set | Phonon-2.5 | Phonon-2.5 English | Qwen3-ASR 1.7B | Qwen3-ASR 0.6B |
| --- | --- | --- | --- | --- |
| LibriSpeech clean | 1.60 | 1.64 | 1.26 | 1.70 |
| LibriSpeech other | 3.41 | 3.56 | 2.94 | 4.01 |
| AMI | 9.12 | 8.76 | 8.31 | 9.33 |
| Earnings-22 | 6.72 | 6.22 | 5.84 | 7.83 |
| GigaSpeech | 8.04 | 7.99 | 7.22 | 7.62 |
| SPGISpeech | 3.31 | 3.31 | 2.57 | 2.74 |
| VoxPopuli | 3.23 | 2.28 | 2.85 | 2.90 |
| Average of the seven | 5.06 | 4.82 | 4.43 | 5.16 |

## Where Qwen3-ASR is the better choice

- Chinese, Cantonese and 22 dialects and accents, plus Japanese, Korean, Thai, Vietnamese, Hindi, Arabic, Indonesian and more.
- English accuracy with the 1.7B model.
- Built-in language identification.
- Low hosted prices on third-party hosts: DeepInfra lists $0.027 per hour for 1.7B and $0.012 for 0.6B.

## Where Phonon-2.5 is the better choice

- Ukrainian, Slovak, Bulgarian, Croatian, Estonian, Latvian, Lithuanian, Slovenian and Maltese, none of which Qwen3-ASR lists.
- Size: 156 MB against 1,565 MB and 4,080 MB.
- No GPU: Phonon runs on laptop and server CPUs; Qwen3-ASR streaming needs the vLLM backend.
- Word timestamps from the model itself in every language, with no second model.

```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

- [Multilingual speech recognition for European languages](https://www.fermionresearch.com/speech/multilingual-speech-recognition-european-languages/)
- [Phonon-2.5 vs Canary](https://www.fermionresearch.com/models/phonon-2-5/vs-canary/)
- [Best open-source speech-to-text model](https://www.fermionresearch.com/speech/best-open-source-speech-to-text-model/)
- [FLEURS results, 25 languages](https://www.fermionresearch.com/speech/fleurs-results-25-languages/)

## Sources and method

- Qwen3-ASR languages, streaming, aligner and toolkits: huggingface.co/Qwen/Qwen3-ASR-1.7B and huggingface.co/Qwen/Qwen3-ASR-0.6B, read 2026-11-13.
- Qwen3-ASR hosted prices: OpenRouter model pages (DeepInfra), read 2026-11-11.
- 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.

Canonical: https://www.fermionresearch.com/models/phonon-2-5/vs-qwen3-asr/

Source: [https://www.fermionresearch.com/models/phonon-2-5/vs-qwen3-asr/](https://www.fermionresearch.com/models/phonon-2-5/vs-qwen3-asr/)
