Downloads · 30 days
188
42% of all-time downloads
Phonon-1-Big
FermionResearch/Phonon-1-Big
Phonon-1-Big is a automatic speech recognition model from FermionResearch. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as apache-2.0.
This is the largest build of the Phonon-1 family, an open speech recognition model for English that downloads in 581 MB.
All-time downloads
450
Public
Repo size
581 MB
Likes
6
Public
Repo makeup
Click a slice to open those files.
.zst581 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- apache-2.0
- Access
- Public
- Created
- Aug 26, 2026
- Updated
- Oct 7, 2026
- SHA
- 74ec0333
Base models
Model card
From the Hugging Face model README
Phonon-1 Big
This is the largest build of the Phonon-1 family, an open speech recognition model for English that downloads in 581 MB.
Benchmarks
| Benchmark | Phonon-1 Big (581 MB) |
|---|---|
| LibriSpeech test-clean | 2.667 |
| LibriSpeech test-other | 5.722 |
| TED-LIUM | 3.400 |
| SPGISpeech | 4.156 |
| VoxPopuli | 8.369 |
| GigaSpeech | 11.291 |
| Earnings-22 | 12.417 |
| AMI | 12.812 |
| Macro (eight benchmarks) | 7.604 |
Word error rate, lower is better. Measured by us — full test sets, Whisper English text normalizer, greedy decoding.
Run it
pip install fermion-research
fermion transcribe phonon-1-big recording.wav
Or serve an OpenAI-compatible endpoint:
fermion serve phonon-1-big
curl -s http://127.0.0.1:8000/v1/audio/transcriptions \
-F "[email protected]" \
-F "model=FermionResearch/Phonon-1-Big"
The same weights run on a Mac (via MLX), on an NVIDIA GPU, or on a plain CPU; the runtimes and Docker images are in the GitHub repo.
License
Apache License 2.0 for the weights and the command line. Base model: Qwen/Qwen3-ASR-0.6B, Apache-2.0.
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- apache-2.0
- Languages
- en
- Created
- Aug 26, 2026
- Updated
- Oct 7, 2026