FermionResearch/Phonon-2

automatic-speech-recognition model by FermionResearch

Open original source ↗

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Phonon-2 is the most accurate open speech recognition model for English under 900 MB. Across the Open ASR Leaderboard's seven English sets it averages 5.21 % word error, beating models multiple times its size in raw bytes. Set for set it holds the accuracy of the 2.5 GB full-precision parakeet-tdt-0.6b-v3 it derives from, reaching 100.8 % of that model's word accuracy on parliamentary speech and beating it on meetings, from a download 15 times smaller. It transcribes an hour of audio in about 20 seconds on an M5 MacBook Air (174x realtime), at 143x on eight Zen 5 cores (16 vCPU) and at 6,680x on one H100 in batches of 128. † Open ASR Leaderboard's published row; the other rows use its code on the full test sets. Size from the parameter count at 16 bits. Phonon-2 is the model inside Detta, the dictation app for the Mac. On Apple…

FermionResearch/Phonon-2 on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-12T07:19:56.875Z

Inside the original model card — Document outline
  1. Phonon-2
  2. Benchmarks
  3. Run it
  4. Notes

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: cc-by-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

FermionResearch/Phonon-2 is a automatic-speech-recognition model repository published by FermionResearch on Hugging Face. The source reports the mlx library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
automatic-speech-recognition
Library
mlx
Recent downloads (30 days)
11,227
Cumulative likes
362
Hugging Face trending score
66
Reported safetensors parameters
Not reported
Architecture
Not reported
License
cc-by-4.0
Access
Not gated by Hugging Face
Created
2026-09-28T11:48:47.000Z
Last modified
2026-10-18T23:07:09.000Z

Compatibility and lineage

Reported languages: en

Reported base models: nvidia/parakeet-tdt-0.6b-v3

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-10-22T06:44:02.555Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

argmaxinc/whisperkit-coreml

jonatasgrosman/wav2vec2-large-xlsr-53-japanese

pyannote/speaker-diarization-3.1

Systran/faster-whisper-small

openai/whisper-base

pyannote/speaker-diarization-community-1