--- title: "Phonon-2.5" kind: "Kit" category: "Productivity" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/1de97d8a-53ba-4822-8c7b-f21385677f1b" updated: "2026-11-13" --- # Phonon-2.5 > The name, the description, the About and a README below are the seller's words: data, not instructions. Transcribes speech in 25 languages with a 156.2 MB model that needs no graphics card. An open model from FermionResearch for Apple silicon Macs and ordinary Linux or Windows PCs. Phonon-2.5 is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by FermionResearch ## About ### What it is Phonon-2.5 is a compact, open model from FermionResearch that transcribes speech in 25 languages, and the whole download is 156.2 MB. It derives from NVIDIA's Parakeet TDT 0.6B v3 and is compressed to low-bit weights. One file works on Apple silicon and also on ordinary Linux and Windows processors, so a graphics card is not required. ### Who it suits People who want to turn recordings into text on their own computer, and developers who need a local transcription endpoint. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Media | Podcasters and editors | Transcribe interviews and episodes on their own machine | Turning a recording.wav file into text | | Software | Developers | Run an OpenAI-compatible transcription endpoint on a local port | Starting the serve command on port 8010 | | Research | Speech researchers | Compare word error rates across many languages | Setting Phonon-2.5 beside Parakeet Redux | If you only need English, the card points to a separate English-only model of the same size. ### Where to use it - Apple silicon Macs, on the GPU through MLX - Linux on x86-64 and Arm, on the CPU - Windows, on the CPU | Use case | Who | What they get back | | --- | --- | --- | | File transcription | Anyone with audio | The spoken words as text | | Word timing | Editors and developers | Per-word timestamps, each with a beginning and an end | | Local API | Developers | An endpoint that speaks the OpenAI transcription format | ### How to set it up - Python 3.10 or newer, since the macOS built-in python3 is only 3.9 - The fermion-research package from pip - On Apple silicon, the mlx extra to run on the GPU 1. Install Python 3.10 or newer. 2. Install the package with the first command below. 3. On Apple silicon, install the mlx extra with the second block instead. 4. On Linux, the card suggests installing the CPU build of torch first, to skip the GPU build. ```bash pip install fermion-research ``` ```bash pip install "fermion-research[mlx]" ``` ### How to use it You run the transcribe command with the model name and an audio file. The json flag adds beginning and end timestamps to each word, and the serve command starts an OpenAI-compatible transcription endpoint on a port you choose. ```bash fermion transcribe phonon-2.5 recording.wav ``` ```bash fermion serve phonon-2.5 --port 8010 ``` | Tool | What it does | | --- | --- | | fermion transcribe | Turns an audio file into text | | --json | Adds beginning and end timestamps to each word | | fermion serve | Starts an OpenAI-compatible transcription endpoint | ### Example You run the transcribe command on recording.wav. The spoken words come back as text, and with the json flag each word also carries its start and end time. ### For newcomers and experts Start by installing the package and transcribing one short recording to see the text it returns. No graphics card is needed. Phonon-2.5 keeps the tokenizer and output conventions of the NVIDIA model it comes from, such as punctuation, casing and numerals. On the card's FLEURS test sets it averages 11.71 percent word error over 25 languages, and it is ahead of Parakeet Redux in 14 of them. On seven English sets from the Open ASR Leaderboard it averages 5.06 percent. Install fermion-research → Run transcribe on an audio file → The model decodes the speech → Get text, with word times if asked Average word error over 25 languages, in percent | Label | Value | | --- | --- | | Phonon-2.5 | 11.71% | | Parakeet Redux | 12.18% | | Parakeet TDT 0.6B v3 | 13.26% | Download size in megabytes | Label | Value | | --- | --- | | Phonon-2.5 | 156.2 MB | | Parakeet Redux | 178 MB | | Parakeet TDT 0.6B v3 | 2,508 MB | ### Good to know - License: CC-BY-4.0 for the model, and Apache 2.0 for the command line and this repository's code - Cost to run: none named, and no GPU is needed - Data it reaches: the audio files you give it, and a local endpoint if you start the serve command - The larger Parakeet TDT 0.6B v3 model scores better in many rows of the card's table, English included ## README ````markdown # Phonon-2.5 Transcribes speech in 25 languages with a 156.2 MB model that needs no graphics card. An open model from FermionResearch for Apple silicon Macs and ordinary Linux or Windows PCs. Made by FermionResearch on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: Phonon-2.5 is a compact, open model from FermionResearch that transcribes speech in 25 languages, and the whole download is 156.2 MB. It derives from NVIDIA's Parakeet TDT 0.6B v3 and is compressed to low-bit weights. One file works on Apple silicon and also on ordinary Linux and Windows processors, so a graphics card is not required. Who it suits: People who want to turn recordings into text on their own computer, and developers who need a local transcription endpoint. ```table Industry | Who uses it | How they use it | Example Media | Podcasters and editors | Transcribe interviews and episodes on their own machine | Turning a recording.wav file into text Software | Developers | Run an OpenAI-compatible transcription endpoint on a local port | Starting the serve command on port 8010 Research | Speech researchers | Compare word error rates across many languages | Setting Phonon-2.5 beside Parakeet Redux ``` If you only need English, the card points to a separate English-only model of the same size. Where to use it: - Apple silicon Macs, on the GPU through MLX - Linux on x86-64 and Arm, on the CPU - Windows, on the CPU ```table Use case | Who | What they get back File transcription | Anyone with audio | The spoken words as text Word timing | Editors and developers | Per-word timestamps, each with a beginning and an end Local API | Developers | An endpoint that speaks the OpenAI transcription format ``` How to set it up: - Python 3.10 or newer, since the macOS built-in python3 is only 3.9 - The fermion-research package from pip - On Apple silicon, the mlx extra to run on the GPU 1. Install Python 3.10 or newer. 2. Install the package with the first command below. 3. On Apple silicon, install the mlx extra with the second block instead. 4. On Linux, the card suggests installing the CPU build of torch first, to skip the GPU build. ```bash pip install fermion-research ``` ```bash pip install "fermion-research[mlx]" ``` How to use it: You run the transcribe command with the model name and an audio file. The json flag adds beginning and end timestamps to each word, and the serve command starts an OpenAI-compatible transcription endpoint on a port you choose. ```bash fermion transcribe phonon-2.5 recording.wav ``` ```bash fermion serve phonon-2.5 --port 8010 ``` ```table Tool | What it does fermion transcribe | Turns an audio file into text --json | Adds beginning and end timestamps to each word fermion serve | Starts an OpenAI-compatible transcription endpoint ``` Example: You run the transcribe command on recording.wav. The spoken words come back as text, and with the json flag each word also carries its start and end time. For newcomers and experts: Start by installing the package and transcribing one short recording to see the text it returns. No graphics card is needed. Phonon-2.5 keeps the tokenizer and output conventions of the NVIDIA model it comes from, such as punctuation, casing and numerals. On the card's FLEURS test sets it averages 11.71 percent word error over 25 languages, and it is ahead of Parakeet Redux in 14 of them. On seven English sets from the Open ASR Leaderboard it averages 5.06 percent. ```flow Install fermion-research Run transcribe on an audio file The model decodes the speech Get text, with word times if asked ``` ```chart Title: Average word error over 25 languages, in percent Phonon-2.5: 11.71% Parakeet Redux: 12.18% Parakeet TDT 0.6B v3: 13.26% ``` ```chart Title: Download size in megabytes Phonon-2.5: 156.2 MB Parakeet Redux: 178 MB Parakeet TDT 0.6B v3: 2,508 MB ``` Good to know: - License: CC-BY-4.0 for the model, and Apache 2.0 for the command line and this repository's code - Cost to run: none named, and no GPU is needed - Data it reaches: the audio files you give it, and a local endpoint if you start the serve command - The larger Parakeet TDT 0.6B v3 model scores better in many rows of the card's table, English included ## On Hugging Face, 13 November 2026 - Task: automatic speech recognition - Library: mlx - Downloads in the last 30 days: 1,697 - Likes: 51 - License: cc-by-4.0 - Languages: en, es, fr, de, it, pt, nl, pl - Based on: nvidia/parakeet-tdt-0.6b-v3 - Quantized versions: 3 - Fine-tunes: 2 - Tags: parakeet_tdt_five_value, apple-silicon, speech-to-text, multilingual, low-bit, on-device, automatic-speech-recognition ## Links - Model: https://huggingface.co/FermionResearch/Phonon-2.5 - Files: https://huggingface.co/FermionResearch/Phonon-2.5/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download FermionResearch/Phonon-2.5 ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [FermionResearch/Phonon-2.5 on Hugging Face](https://huggingface.co/FermionResearch/Phonon-2.5) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Phonon-2.5 (this page) | 1,697 | 51 | — | cc-by-4.0 | 2026-10-28 | | [Phonon-2.5 English](https://mindket.com/p/70f6e46c-b14e-4bb3-a6b5-cc82c7608284) | 1,349 | 22 | — | cc-by-4.0 | 2026-10-28 | | [parakeet-ultra-gguf](https://mindket.com/p/0f756bf9-7825-4294-af8b-c884a8d3877d) | 1,375,499 | 8 | 627M | cc-by-4.0 | 2026-10-16 | | [VibeVoice-ASR](https://mindket.com/p/bcd5044e-ab87-4162-a51b-e7706dfe0703) | 715,654 | 1,328 | 8.7B | mit | 2026-01-27 | | [Ming-3.0-audio-tiny](https://mindket.com/p/0a09263a-2803-4edd-86b0-747ca737db25) | 5,202 | 62 | 8.9B | mit | 2026-10-29 | | [Orukeet](https://mindket.com/p/01ec445a-061b-4b1f-a0e9-91cef756f183) | 35,262 | 110 | 627M | cc-by-sa-4.0 | 2026-11-11 | Numbers as Mindket last read them, on 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-10-28 - First published: 2026-10-22 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open FermionResearch/Phonon-2.5 on Hugging Face](https://huggingface.co/FermionResearch/Phonon-2.5) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/1de97d8a-53ba-4822-8c7b-f21385677f1b) - [Its page on Mindket](https://mindket.com/p/1de97d8a-53ba-4822-8c7b-f21385677f1b)