---
title: "Phonon-2.5 vs Whisper large-v3-turbo"
description: "Phonon-2.5 averages 5.06 % English word error on seven Open ASR sets, Whisper large-v3-turbo 6.58 %, at 156 MB against 1,618 MB. Turbo covers 99 languages."
canonical: "https://www.fermionresearch.com/models/phonon-2-5/vs-whisper-large-v3-turbo/"
source: "Fermion Research"
---

Phonon/facts checked 13 November 2026

# Phonon-2.5 vs Whisper large-v3-turbo

Two open speech models you can run yourself. Whisper large-v3-turbo is OpenAI's faster Whisper with 99 languages; Phonon-2.5 covers 25 European languages from a tenth of the download.

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

## The short answer

Pick Phonon-2.5 when your audio is in one of its 25 European languages: on the seven English test sets of the Open ASR Leaderboard it averages 5.06 % word error against 6.58 % for Whisper large-v3-turbo, from a 156 MB download against 1,618 MB. Pick Whisper large-v3-turbo when you need a language outside those 25 (its model card lists 99) or speech translation into English.

Across Phonon-2.5's 25 languages on the FLEURS test sets, the Phonon-2.5 release post reports a lower average word error for Phonon-2.5 than for Whisper large-v3-turbo. Phonon-2.5 English, the English-only model, averages 4.82 % on the seven English sets.

## Side by side

Whisper facts from OpenAI's model card on Hugging Face, read 2026-11-13. Hosted prices are list prices from third-party hosts; OpenAI publishes the weights.

|  | Phonon-2.5 | Whisper large-v3-turbo |
| --- | --- | --- |
| Model type | Open weights on Hugging Face | Open weights on Hugging Face |
| Size | 156 MB download (Phonon-2.5 English: 158 MB) | 809 M parameters, 1,618 MB |
| Languages | 25 European languages (Phonon-2.5 English: English only) | 99 |
| English word error, seven Open ASR sets | 5.06 % (Phonon-2.5 English: 4.82 %) | 6.58 % |
| Hosted price per audio hour | No per-hour fee when self-hosted | DeepInfra $0.012; Groq $0.04 (third-party hosts) |
| Where it runs | Your hardware: CPUs (Linux x86-64 and arm64, Windows x86-64), Apple silicon, NVIDIA GPUs, Android | GPU or CPU through Transformers, whisper.cpp and other runtimes |
| Streaming | Yes, live WebSocket from fermion serve | Chunked long-form decoding in Transformers |
| Speech translation to English | No | Yes |
| Word timestamps | Yes (--json output) | Yes (return_timestamps="word") |

## English, set by set

Phonon-2.5 has the lower word error on six of the seven sets. Whisper large-v3-turbo is ahead on SPGISpeech (financial dictation), 2.79 % against 3.31 %. The widest gaps are AMI meetings (13.88 % against 9.12 %) and VoxPopuli parliamentary speech (7.02 % against 3.23 %).

| Test set | Phonon-2.5 | Phonon-2.5 English | Whisper large-v3-turbo |
| --- | --- | --- | --- |
| LibriSpeech clean | 1.60 | 1.64 | 2.13 |
| LibriSpeech other | 3.41 | 3.56 | 3.71 |
| AMI | 9.12 | 8.76 | 13.88 |
| Earnings-22 | 6.72 | 6.22 | 8.09 |
| GigaSpeech | 8.04 | 7.99 | 8.47 |
| SPGISpeech | 3.31 | 3.31 | 2.79 |
| VoxPopuli | 3.23 | 2.28 | 7.02 |
| Average of the seven | 5.06 | 4.82 | 6.58 |

## Where Whisper large-v3-turbo is the better choice

- Languages outside Europe: Chinese, Japanese, Arabic, Hindi, Korean, Turkish and the rest of Whisper's 99.
- Translation: setting the task to "translate" produces English text from speech in another language. Phonon transcribes only.
- Existing Whisper tooling: whisper.cpp, faster-whisper and many hosted endpoints already serve it; DeepInfra lists it at $0.00020 per minute ($0.012 per audio hour).
- Financial dictation in English: its SPGISpeech score is lower than Phonon-2.5's.

## Where Phonon-2.5 is the better choice

- English accuracy on meetings, earnings calls, podcasts and parliamentary speech: lower word error on six of seven sets.
- Size: 156 MB fits a phone, a laptop app or a small container; turbo is 1,618 MB.
- Live transcription: fermion serve exposes a WebSocket stream next to the file route.
- Verbatim output: Phonon keeps repetitions and short responses such as "Mm-hmm" as spoken.

```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 Whisper (large-v3 and base)](https://www.fermionresearch.com/models/phonon-2-5/vs-whisper/)
- [Whisper alternatives](https://www.fermionresearch.com/speech/whisper-alternatives/)
- [English benchmark results](https://www.fermionresearch.com/speech/english-benchmark-results/)
- [Self-host a speech-to-text server](https://www.fermionresearch.com/models/phonon-2-5/self-host/)

## Sources and method

- Whisper large-v3-turbo parameters, languages, translation and timestamps: huggingface.co/openai/whisper-large-v3-turbo, read 2026-11-13.
- DeepInfra price: deepinfra.com/openai/whisper-large-v3-turbo, read 2026-11-13. Groq price: OpenRouter model pages, 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).
- 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.
- FLEURS comparison: Phonon-2.5 release post (/research/phonon-2-5/), full FLEURS test sets, one scoring code for all models.

Canonical: https://www.fermionresearch.com/models/phonon-2-5/vs-whisper-large-v3-turbo/

Source: [https://www.fermionresearch.com/models/phonon-2-5/vs-whisper-large-v3-turbo/](https://www.fermionresearch.com/models/phonon-2-5/vs-whisper-large-v3-turbo/)
