Research
Introducing Phonon-2.5
Open speech recognition in 25 languages from a 156 MB download, and a new English model of the same size. Both run on a laptop CPU at the speed of Phonon-2.
Speech recognition · 25 languages · Available nowPhonon-2.5
Open speech recognition in 25 languages from a 156 MB download. 11.71 % average word error on the FLEURS test sets, ahead of Parakeet Redux at the same size and of the 2.5 GB Parakeet TDT 0.6B v3 it derives from.
- 156 MB
- Download, 178 MB on disk
- 25
- Languages, one file
- 11.71 %
- FLEURS word error, average of 25
- 14 of 25
- Languages ahead of Parakeet Redux
- 5.06 %
- Seven-set English word error
Overview
Phonon-2.5 is an open speech recognition model for 25 languages in a 156 MB download. On the FLEURS test sets it averages 11.71 % word error across the 25 languages, against 12.18 % for Parakeet Redux, the other low-bit model of the same size, and 13.26 % for Parakeet TDT 0.6B v3, the 2.5 GB full-precision model it derives from. It is ahead of Redux in 14of the 25 languages, and it holds 101.8 % of the base’s word accuracy averaged over the 25, ahead of the base outright in 14 of them (Greek 20.8 against 36.1, Latvian 14.9 against 23.7, Slovenian 18.5 against 24.7), where a standard post-training 4-bit Parakeet v3 (472 MB) is worse than the base in all 25 at 14.48 %. It is a lower average word error rate across the 25 languages than Whisper large-v3 (20 times its size), Meta MMS-1B-all (25 times), Parakeet TDT 0.6B v3 (16 times) and Whisper large-v3-turbo (10 times); Whisper base, about the same size, makes 4.6 times as many errors (53.71 % against 11.71 %).
The same file runs on Apple silicon and on Linux (x86-64 and Arm) and Windows CPUs, with no GPU needed, on NVIDIA GPUs and in the CPU and CUDA Docker images. There is no language setting: it detects the language from the audio. It writes punctuated, capitalized text with a start and end time for every word, and the weights are released under CC-BY-4.0. For English alone, Phonon-2.5 English is the same size and our most accurate English model.
Models
Phonon-2.5 is a single file. Phonon-2.5 English and Phonon-2 remain available beside it.
- Phonon-2.525 languages
- 156 MB download · 178 MB on disk
- Phonon-2.5 EnglishEnglish
- 158 MB download · 178 MB on disk
- Phonon-2English; the earlier model
- 164 MB download · 177 MB on disk
- LanguagesEnglish, Spanish, French, German, Italian, Portuguese, Dutch, Polish, Russian, Ukrainian, Romanian, Czech, Slovak, Bulgarian, Croatian, Swedish, Danish, Finnish, Estonian, Latvian, Lithuanian, Hungarian, Slovenian, Maltese, Greek
- 25
- Audio inputmicrophone or file
- 16 kHz
- Outputwith a start and end time for every word
- Punctuated, capitalized text
Evaluation
All three models were scored on the full FLEURS test set of each of the 25 languages with the same harness and the same text normalisation. Table 1 lists every language; the average over the 25 is 11.71 % for Phonon-2.5, 12.18 % for Parakeet Redux and 13.26 % for Parakeet TDT 0.6B v3.
| Language | Phonon-2.5156 MB | Parakeet Redux178 MB | Parakeet TDT 0.6B v32,508 MB |
|---|---|---|---|
| English | 6.58 | 7.32 | 6.53 |
| Spanish | 4.80 | 4.99 | 4.69 |
| French | 8.12 | 9.03 | 6.61 |
| German | 6.67 | 7.57 | 5.96 |
| Italian | 5.21 | 5.12 | 4.75 |
| Portuguese | 6.53 | 6.44 | 6.27 |
| Dutch | 9.21 | 9.45 | 7.93 |
| Polish | 10.20 | 10.19 | 8.55 |
| Russian | 8.67 | 9.01 | 7.21 |
| Ukrainian | 7.89 | 8.05 | 7.27 |
| Romanian | 11.88 | 11.89 | 13.13 |
| Czech | 10.40 | 11.41 | 11.93 |
| Slovak | 8.89 | 8.17 | 9.72 |
| Bulgarian | 13.34 | 13.02 | 13.48 |
| Croatian | 12.24 | 11.43 | 13.21 |
| Swedish | 14.53 | 14.70 | 15.44 |
| Danish | 18.20 | 17.91 | 19.05 |
| Finnish | 12.02 | 11.84 | 13.08 |
| Estonian | 11.91 | 10.29 | 14.34 |
| Latvian | 14.92 | 14.76 | 23.66 |
| Lithuanian | 17.94 | 18.05 | 21.68 |
| Hungarian | 15.45 | 15.81 | 15.38 |
| Slovenian | 18.53 | 18.88 | 24.70 |
| Maltese | 17.91 | 16.02 | 20.86 |
| Greek | 20.83 | 33.25 | 36.11 |
| Average of 25 | 11.71 | 12.18 | 13.26 |
English
- Phonon-2.5
- 6.58
- Parakeet Redux
- 7.32
- Parakeet TDT 0.6B v3
- 6.53
Spanish
- Phonon-2.5
- 4.80
- Parakeet Redux
- 4.99
- Parakeet TDT 0.6B v3
- 4.69
French
- Phonon-2.5
- 8.12
- Parakeet Redux
- 9.03
- Parakeet TDT 0.6B v3
- 6.61
German
- Phonon-2.5
- 6.67
- Parakeet Redux
- 7.57
- Parakeet TDT 0.6B v3
- 5.96
Italian
- Phonon-2.5
- 5.21
- Parakeet Redux
- 5.12
- Parakeet TDT 0.6B v3
- 4.75
Portuguese
- Phonon-2.5
- 6.53
- Parakeet Redux
- 6.44
- Parakeet TDT 0.6B v3
- 6.27
Dutch
- Phonon-2.5
- 9.21
- Parakeet Redux
- 9.45
- Parakeet TDT 0.6B v3
- 7.93
Polish
- Phonon-2.5
- 10.20
- Parakeet Redux
- 10.19
- Parakeet TDT 0.6B v3
- 8.55
Russian
- Phonon-2.5
- 8.67
- Parakeet Redux
- 9.01
- Parakeet TDT 0.6B v3
- 7.21
Ukrainian
- Phonon-2.5
- 7.89
- Parakeet Redux
- 8.05
- Parakeet TDT 0.6B v3
- 7.27
Romanian
- Phonon-2.5
- 11.88
- Parakeet Redux
- 11.89
- Parakeet TDT 0.6B v3
- 13.13
Czech
- Phonon-2.5
- 10.40
- Parakeet Redux
- 11.41
- Parakeet TDT 0.6B v3
- 11.93
Slovak
- Phonon-2.5
- 8.89
- Parakeet Redux
- 8.17
- Parakeet TDT 0.6B v3
- 9.72
Bulgarian
- Phonon-2.5
- 13.34
- Parakeet Redux
- 13.02
- Parakeet TDT 0.6B v3
- 13.48
Croatian
- Phonon-2.5
- 12.24
- Parakeet Redux
- 11.43
- Parakeet TDT 0.6B v3
- 13.21
Swedish
- Phonon-2.5
- 14.53
- Parakeet Redux
- 14.70
- Parakeet TDT 0.6B v3
- 15.44
Danish
- Phonon-2.5
- 18.20
- Parakeet Redux
- 17.91
- Parakeet TDT 0.6B v3
- 19.05
Finnish
- Phonon-2.5
- 12.02
- Parakeet Redux
- 11.84
- Parakeet TDT 0.6B v3
- 13.08
Estonian
- Phonon-2.5
- 11.91
- Parakeet Redux
- 10.29
- Parakeet TDT 0.6B v3
- 14.34
Latvian
- Phonon-2.5
- 14.92
- Parakeet Redux
- 14.76
- Parakeet TDT 0.6B v3
- 23.66
Lithuanian
- Phonon-2.5
- 17.94
- Parakeet Redux
- 18.05
- Parakeet TDT 0.6B v3
- 21.68
Hungarian
- Phonon-2.5
- 15.45
- Parakeet Redux
- 15.81
- Parakeet TDT 0.6B v3
- 15.38
Slovenian
- Phonon-2.5
- 18.53
- Parakeet Redux
- 18.88
- Parakeet TDT 0.6B v3
- 24.70
Maltese
- Phonon-2.5
- 17.91
- Parakeet Redux
- 16.02
- Parakeet TDT 0.6B v3
- 20.86
Greek
- Phonon-2.5
- 20.83
- Parakeet Redux
- 33.25
- Parakeet TDT 0.6B v3
- 36.11
Average of 25
- Phonon-2.5
- 11.71
- Parakeet Redux
- 12.18
- Parakeet TDT 0.6B v3
- 13.26
On the Open ASR Leaderboard’s seven English sets, scored with its code on the full test sets, Phonon-2.5 averages 5.06 % word error, against 5.21 % for Phonon-2 and 4.82 % for Phonon-2.5 English: a better English model than Phonon-2 while covering 24 more languages, from a smaller download.
| Model | Download | LS clean | LS other | AMI | Earnings-22 | GigaSpeech | SPGISpeech | VoxPopuli | Average |
|---|---|---|---|---|---|---|---|---|---|
| Phonon-2.5 English | 158 MB | 1.64 | 3.56 | 8.76 | 6.22 | 7.99 | 3.31 | 2.28 | 4.82 |
| Phonon-2.525 languages | 156 MB | 1.60 | 3.41 | 9.12 | 6.72 | 8.04 | 3.31 | 3.23 | 5.06 |
| Phonon-2 | 164 MB | 1.72 | 3.92 | 9.37 | 6.96 | 8.35 | 3.70 | 2.46 | 5.21 |
| Underdog Bark 3.0 | 163 MB | 1.89 | 4.08 | 7.82 | 7.05 | 7.95 | 3.72 | 2.05 | 4.94 |
| Parakeet TDT 0.6B v3† | 2,508 MB | 1.52 | 3.13 | 9.42 | 5.85 | 7.99 | 3.63 | 3.19 | 4.96 |
| Parakeet Redux | 178 MB | 1.94 | 4.35 | 9.16 | 7.90 | 8.62 | 4.01 | 3.87 | 5.69 |
Phonon-2.5 English158 MB
- LS clean
- 1.64
- LS other
- 3.56
- AMI
- 8.76
- Earnings-22
- 6.22
- GigaSpeech
- 7.99
- SPGISpeech
- 3.31
- VoxPopuli
- 2.28
- Average
- 4.82
Phonon-2.525 languages156 MB
- LS clean
- 1.60
- LS other
- 3.41
- AMI
- 9.12
- Earnings-22
- 6.72
- GigaSpeech
- 8.04
- SPGISpeech
- 3.31
- VoxPopuli
- 3.23
- Average
- 5.06
Phonon-2164 MB
- LS clean
- 1.72
- LS other
- 3.92
- AMI
- 9.37
- Earnings-22
- 6.96
- GigaSpeech
- 8.35
- SPGISpeech
- 3.70
- VoxPopuli
- 2.46
- Average
- 5.21
Underdog Bark 3.0163 MB
- LS clean
- 1.89
- LS other
- 4.08
- AMI
- 7.82
- Earnings-22
- 7.05
- GigaSpeech
- 7.95
- SPGISpeech
- 3.72
- VoxPopuli
- 2.05
- Average
- 4.94
Parakeet TDT 0.6B v3†2,508 MB
- LS clean
- 1.52
- LS other
- 3.13
- AMI
- 9.42
- Earnings-22
- 5.85
- GigaSpeech
- 7.99
- SPGISpeech
- 3.63
- VoxPopuli
- 3.19
- Average
- 4.96
Parakeet Redux178 MB
- LS clean
- 1.94
- LS other
- 4.35
- AMI
- 9.16
- Earnings-22
- 7.90
- GigaSpeech
- 8.62
- SPGISpeech
- 4.01
- VoxPopuli
- 3.87
- Average
- 5.69
Speed
Phonon-2.5 has the architecture, the file format and the engines of Phonon-2, so it runs at about the same speed as Phonon-2, and it will get a lot faster in the coming weeks. For reference, these are Phonon-2’s published figures, from its release post: 174 times realtime on a base M5 MacBook Air, which is an hour of audio in about 20 seconds; 143 times realtime on eight AMD Zen 5 cores; and 6,680 times realtime batched on an H100.
Run it
Python 3.10 or newer. The fermion command line installs from PyPI; name the model as phonon-2.5.
$ pip install fermion-research$ fermion transcribe phonon-2.5 meeting.wav$ fermion transcribe phonon-2.5 meeting.wav --json$ fermion serve phonon-2.5 --port 8010
It transcribes files, adds a start and end time for every word under --json, and serves an OpenAI-compatible /v1/audio/transcriptions endpoint.
$ pip install "fermion-research[mlx]"
On Apple silicon it runs the model on the GPU through MLX.
$ pip install --no-deps torch --index-url https://download.pytorch.org/whl/cpu$ pip install fermion-research
On Linux (x86-64 and Arm) and Windows the same package runs the CPU engine; on Linux, install torch from its CPU wheel index first to skip the GPU build.
Weights on Hugging FaceDocumentationfermion-research on PyPIEngines on GitHub
Availability
Open weightsCC-BY-4.025 languagesApple siliconNVIDIA GPUsCPUs
License
The weights are released under the Creative Commons Attribution 4.0 licence, which Phonon-2.5 inherits from NVIDIA’s Parakeet TDT 0.6B v3; the repository’s NOTICE carries the attribution and lists the changes. The licence permits commercial use, modification and redistribution with attribution. The command line is released under Apache 2.0.
Citation
@misc{fermionresearch2026phonon25,
title = {Phonon-2.5},
author = {{Fermion Research}},
year = {2026},
url = {https://fermionresearch.com/models/phonon-2-5/}
}