Audio modelOpen weights
Phonon-2
Fermion Research
- Released
- -
- Data date
- October 3, 2026
- Model class
- Access
Phonon-2 is a heavily compressed English ASR derivative of NVIDIA Parakeet TDT 0.6B. Quantized weights bring it below 900 MB and target local execution rather than claiming a new foundation model.
The model card reports 5.21% word error rate across seven English datasets and roughly 174 times real-time on an M5 MacBook Air. CC-BY-4.0 applies to this derivative.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Compressed speech recognitionSource |
| Access | Local weightsSource |
| Input | English audioSource |
| Output | TranscriptSource |
| Checkpoint | FermionResearch/Phonon-2Source |
| License | CC-BY-4.0Source |
| Derived from | Quantized derivative of nvidia/parakeet-tdt-0.6b-v3, not a new foundation modelSource |
| Compression | About 2.1 bits per weight and under 900 MBSource |
| Reported WER | 5.21% across seven English datasetsSource |
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
average WER (Show measurement, test conditions, and source)
- Source value
- 5.21
- Score
- 5.21
- Metric
- word error rate
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Phonon-2 model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. LS-clean 1.72, LS-other 3.92, AMI 9.37, Earnings22 6.96, GigaSpeech 8.35, SPGISpeech 3.70, VoxPopuli 2.46
- Context
- Source-specific observation; it does not establish a compatible cross-model cohort.
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Additional source | Phonon-2 model card (retrieved October 3, 2026; October 4, 2026) · Phonon-2 model card · Editorial description reviewed October 3, 2026 |