Phonon-2

FermionResearch/Phonon-2

Speech RecognitionmlxLicense: cc-by-4.0
Tracked by OpenModelStats since September 28, 2026View on Hugging Face ↗
Downloads 30D
3,750
Total downloads
3,750
Gained 7D
—
Gained 30D
—
Likes
271
Rank · tracked models
#13,998
1066(up 1066 places)this week
Parameters
—
Last source update
Oct 7, 2026
  • It moved from #483 to #459 among tracked Speech Recognition models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Phonon-2 is a speech recognition model published by FermionResearch. OpenModelStats has tracked the model since Sep 28, 2026, most recently observing it 3h ago.

Published
Sep 28, 2026
Last updated
Oct 7, 2026
Library
mlx
License
cc-by-4.0
Task
Speech Recognition
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
—
mlxparakeet_tdt_five_valueapple-siliconspeech-to-textasrsttlow-bitquantization-aware-trainingon-deviceautomatic-speech-recognitionenbase_model:nvidia/parakeet-tdt-0.6b-v3

Publisher

FermionResearchView publisher statistics →

Derived from nvidia/parakeet-tdt-0.6b-v3 (reported by the source; parent not yet tracked).

Similar models

Models similar to Phonon-2
ModelDL 30D
wav2vec2-large-xlsr-53-japanesejonatasgrosman16.2M
whisperkit-coremlargmaxinc10.8M
speaker-diarization-3.1pyannote7.2M
whisper-large-v3-turboopenai6.3M
wav2vec2-large-xlsr-53-portuguesejonatasgrosman5.6M
speaker-diarization-community-1pyannote5.6M
FermionResearch/Phonon-2 — Downloads, Growth & Stats | OpenModelStats