Model reference · open weights
parakeet-unified-en is an open-weight audio or speech model from handy-computer, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
parakeet-unified-en-0.6b: transcribe.cpp GGUF GGUF conversions of nvidia/parakeet-unified-en-0.6b for use with transcribe.cpp. Ported from upstream commit d4ac992, pinned 2026-05-10. Validated against the NeMo reference at transcribe.cpp commit 42528dd on 2026-05-10. Offline English speech-to-text with punctuation and capitalization. A 0.6B-parameter FastConformer encoder with an RNN-T transducer decoder, trained as a 'unified' streaming/offline model. This port runs the model in offline mode only — streaming attention contexts are present in the GGUF but transcribe.cpp does not yet expose a streaming entry. Downloads WER measured on the full LibriSpeech test-clean split (2620 utterances) with greedy RNN-T decoding and no external LM. F32 reference baseline: 1.59%. NVIDIA's self-reported number on the same split is 1.63%. Usage Build transcribe.cpp from source: Run on a 16 kHz mono WAV: If your audio isn't already 16 kHz mono WAV, convert it first: See the transcribe.cpp model page for performance numbers, numerical validation, and reproduction steps. License Inherited from the base model: CC-BY-4.0. See the upstream model card for full terms. Original Model Card The section below is reproduced from nvidia/parakeet-unified-en-0.6b at commit d4ac992 for offline reference. The upstream card is the authoritative source. 🦜Parakeet-unified-en-0.6b: Unified ASR model for offline and streaming inference Parakeet-unified-en-0.6b is an English automatic speech recognition (ASR) model based on transducer architecture (RNN-T) combining both offline and streaming inference (with a minimum latency of 160ms) in one model [1]. It is trained mostly on the English part of the Granary dataset [4], which contains approximately 250,000 hours of US English (en-US) speech across diverse acoustic conditions. The model transcribes speech to English alphabet, spaces, and apostrophes with punctuation and captalization support. Average WER comparison on the HF ASR Leaderboard datasets including offline and streaming inference with different latency values. Why Choose nvidia/parakeet-unified-en-0.6b? - One model for both tasks: You need to utilize only one unified model for both offline an
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | handy-computer |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | transcribe.cpp |
| Based on | nvidia/parakeet-unified-en-0.6b |
| Released | 2026-05-10 |
| Popularity | 1.7M downloads / month |
| Likes | 4 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| parakeet-unified-en-0.6b-gguf | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys parakeet-unified-en for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (parakeet-unified-en below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="parakeet-unified-en" -F file=@audio.mp3
Details
Languages
Tags
Papers
Licence
Open weights under cc-by-4.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗