{"id":8449,"date":"2026-10-01T08:12:06","date_gmt":"2026-09-30T23:12:06","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/01\/phonon-2-open-weight-english-asr-model\/"},"modified":"2026-10-01T23:09:09","modified_gmt":"2026-10-01T14:09:09","slug":"phonon-2-open-weight-english-asr-model","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/01\/phonon-2-open-weight-english-asr-model\/","title":{"rendered":"Phonon-2 Speech Recognition Model: 4GB+ VRAM"},"content":{"rendered":"

<\/p>\n

At a Glance<\/h2>\n
\n\n\n\n\n\n\n\n\n\n\n
Item<\/th>\nValue<\/th>\n<\/tr>\n<\/thead>\n
Repository<\/td>\nFermionResearch\/Phonon-2<\/a><\/td>\n<\/tr>\n
Publisher guide<\/td>\nNVIDIA: models and licenses<\/a><\/td>\n<\/tr>\n
Published<\/td>\n2026-09-28<\/td>\n<\/tr>\n
License<\/td>\ncc-by-4.0<\/td>\n<\/tr>\n
Formats<\/td>\nMLX<\/a><\/td>\n<\/tr>\n
Source type<\/td>\nPrimary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Values determined by this site’s code when the information was collected. Dates are JST.<\/em><\/p>\n

<\/p>\n

Overview<\/h2>\n

FermionResearch has released “Phonon-2”, an open-weight model that achieves both extremely high accuracy and lightweight performance in English Automatic Speech Recognition (ASR). This model is a Speech-to-Text model that takes audio files as input and outputs text properly containing punctuation, capitalization, and numerical notation.<\/p>\n

Phonon-2 adopts NVIDIA’s “nvidia\/parakeet-tdt-0.6b-v3” as its base model and applies proprietary quantization techniques, making it reported to be the most accurate open English speech recognition model under 900 MB. A major feature is that compared to the full-precision teacher model of about 2.5 GB, it maintains equivalent accuracy while reducing the download size by 15x.<\/p>\n

Specifications<\/h2>\n

The main specifications of Phonon-2 and its base model based on the documentation are as follows:<\/p>\n