Announcement
Introducing Phonon-1
An open speech recognition model for English in a 415 MB download. It runs on a laptop or a datacenter GPU and transcribes an hour of audio in about two and a half minutes.
Speech recognition · Available nowPhonon-1
An open speech recognition model for English in a 415 MB download. It runs on a laptop or a datacenter GPU and transcribes an hour of audio in about two and a half minutes.
- 415 MB
- Download, 455 MB on disk
- 2.640 %
- LibriSpeech test-clean
- 23.9×
- Realtime, median of nine corpora
- Apache-2.0
- Open weights
Phonon-1 is an open speech recognition model for English. It downloads in 415 MB, runs on a laptop or a datacenter GPU, and transcribes an hour of audio in about two and a half minutes. It was trained at 2.4 bits per weight from the start, and it is the second model in the lab’s low-bit lane after Neutrino-1.
Output arrives punctuated and capitalized from the model itself. Phonon-1 was the first model inside Detta, the Fermion Research dictation app for the Mac, which now runs Phonon-2.
- Phonon-1the earlier model
- 415 MB download · 455 MB on disk
- Phonon-1 Microthe smallest model; the accuracy trade is in the table below
- 285 MB download · 331 MB on disk
- Language
- English
- Audio inputmicrophone or file
- 16 kHz
- Output
- Punctuated, capitalized text
Benchmarks
| Benchmark | Phonon-1415 MB | Phonon-1 Micro285 MB | Parakeet-0.6B 4-bit637 MB | Moonshine base248 MB | Whisper large-v3-turbo1,619 MB | Whisper small967 MB | wav2vec2-large1,262 MB | Qwen3-ASR teacher1,569 MB |
|---|---|---|---|---|---|---|---|---|
| LibriSpeech test-clean | 2.640 | 3.002 | 2.186 | 3.417 | 2.10 | 3.4† | 2.8† | 2.235 |
| LibriSpeech test-other | 5.699 | 6.511 | 3.937 | 8.262 | 4.07 | 7.6† | 6.3† | 4.618 |
| TED-LIUM | 3.421 | 3.878 | 2.829 | 5.272 | – | – | – | 2.889 |
| SPGISpeech | 4.163 | 4.858 | 4.104 | 5.731 | 2.79† | – | 13.31† | 3.074 |
| VoxPopuli | 8.394 | 9.177 | 6.345 | 10.470 | 11.22† | – | – | 7.151 |
| GigaSpeech | 11.396 | 11.882 | 9.614 | 12.114 | 8.52† | – | – | 9.321 |
| Earnings-22 | 12.571 | 14.771 | 11.190 | 17.872 | 11.07† | – | 36.28† | 11.188 |
| AMI | 13.084 | 14.094 | 12.723 | 17.790 | 15.16† | – | – | 12.560 |
| Macro, eight benchmarks | 7.67 | 8.52 | 6.62 | 10.1 | – | – | – | 6.63 |
The Phonon-2 pages score Phonon-1 with the Open ASR Leaderboard’s own code on its seven sets, where it reads 2.11 on LibriSpeech test-clean, 5.03 on test-other and 6.56 on average. The figures above use the Whisper English normaliser, so the two sets of numbers differ.
Speed
Median 23.9× realtime across nine corpora on a base M5 MacBook Air.
- Phonon-1
- p50 262 ms · p95 629 ms
- Fastest build of the family
- p50 203 ms · p95 446 ms
Run it
Apple silicon, on the GPU through MLX:
$ pip install fermion-research$ fermion transcribe phonon-1 recording.wav
One-shot file transcription. fermion listen transcribes the microphone live; fermion serve exposes an OpenAI-compatible transcription route.
$ fermion listen phonon-1$ fermion serve phonon-1
NVIDIA GPUs, through the CUDA container:
$ docker run --rm --gpus all ghcr.io/fermionresearch/phonon-cuda:0.3.0 \transcribe recording.wav --model phonon-1
CPUs, with no GPU at all, on macOS, Linux, and Windows:
$ pip install fermion-research torch safetensors soundfile scipy zstandarddocker run --rm ghcr.io/fermionresearch/phonon-cpu:0.1.0 \transcribe recording.wav --model phonon-1
The containers transcribe recordings of any length, stream over WebSocket, and serve the same endpoint as fermion serve.
The runtimes and Docker images are in the GitHub repository.
Weights on Hugging Facefermion-research on PyPIRuntimes on GitHub
Availability
Open weightsApache-2.0
License
Open weights under the Apache License 2.0. Commercial use, modification, fine-tuning, and redistribution are permitted, with no access request and no acceptance form. The model is a derivative of Qwen/Qwen3-ASR-0.6B, itself Apache-2.0; the command line is Apache-2.0 too.
Citation
@misc{fermionresearch2026phonon,
title = {Phonon-1},
author = {{Fermion Research}},
year = {2026},
url = {https://fermionresearch.com/models/phonon-1/}
}