Model reference · open weights
parakeet-tdt is an open-weight audio or speech model from nvidia, 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
<span style="color:#76b900;"🦜 parakeet-tdt-0.6b-v3: Multilingual Speech-to-Text Model</span img { display: inline; } [](#model-architecture) <span style="color:#466f00;"Description:</span parakeet-tdt-0.6b-v3 is a 600-million-parameter multilingual automatic speech recognition (ASR) model designed for high-throughput speech-to-text transcription. It extends the parakeet-tdt-0.6b-v2 model by expanding language support from English to 25 European languages. The model automatically detects the language of the audio and transcribes it without requiring additional prompting. It is part of a series of models that leverage the Granary [1, 2] multilingual corpus as their primary training dataset. 🗣️ Try Demo here: https://huggingface.co/spaces/nvidia/parakeet-tdt-0.6b-v3 Supported Languages: Bulgarian (bg), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Finnish (fi), French (fr), German (de), Greek (el), Hungarian (hu), Italian (it), Latvian (lv), Lithuanian (lt), Maltese (mt), Polish (pl), Portuguese (pt), Romanian (ro), Slovak (sk), Slovenian (sl), Spanish (es), Swedish (sv), Russian (ru), Ukrainian (uk) This model is ready for commercial/non-commercial use. <span style="color:#466f00;"Key Features:</span parakeet-tdt-0.6b-v3's key features are built on the foundation of its predecessor, parakeet-tdt-0.6b-v2, and include: Automatic punctuation and capitalization Accurate word-level and segment-level timestamps Long audio transcription, supporting audio up to 24 minutes long with full attention (on A100 80GB) or up to 3 hours with local attention. Released under a permissive CC BY 4.0 license For full details on the model architecture, training methodology, datasets, and evaluation results, check out the Technical Report. <span style="color:#466f00;"License/Terms of Use:</span GOVERNING TERMS: Use of this model is governed by the CC-BY-4.0 license. <span style="color:#466f00;"Discover more from NVIDIA:</span For documentation, deployment guides, enterprise-ready APIs, and the latest open models—including Nemotron and other cutting-edge speech, translation, and generative AI—visit the NVIDIA Developer Portal at developer.nvidia.com. Joi
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | nvidia |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 627M |
| Variants | 2 |
| Runs with | transformers |
| Released | 2025-08-04 |
| Popularity | 744k downloads / month |
| Likes | 1,538 |
| 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.
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Automatic Speech Recognition | AMI (Meetings test) | Test WER | 11.31 |
| Automatic Speech Recognition | Earnings-22 | Test WER | 11.42 |
| Automatic Speech Recognition | GigaSpeech | Test WER | 9.59 |
| Automatic Speech Recognition | LibriSpeech (clean) | Test WER | 1.93 |
| Automatic Speech Recognition | LibriSpeech (clean) | Test WER | 3.59 |
| automatic-speech-recognition | SPGI Speech | Test WER | 3.97 |
| automatic-speech-recognition | tedlium-v3 | Test WER | 2.75 |
| Automatic Speech Recognition | Vox Populi | Test WER | 6.14 |
| automatic-speech-recognition | FLEURS | Test WER (Bg) | 12.64 |
| automatic-speech-recognition | FLEURS | Test WER (Cs) | 11.01 |
| automatic-speech-recognition | FLEURS | Test WER (Da) | 18.41 |
| automatic-speech-recognition | FLEURS | Test WER (De) | 5.04 |
| automatic-speech-recognition | FLEURS | Test WER (El) | 20.7 |
| automatic-speech-recognition | FLEURS | Test WER (En) | 4.85 |
| automatic-speech-recognition | FLEURS | Test WER (Es) | 3.45 |
| automatic-speech-recognition | FLEURS | Test WER (Et) | 17.73 |
| automatic-speech-recognition | FLEURS | Test WER (Fi) | 13.21 |
| automatic-speech-recognition | FLEURS | Test WER (Fr) | 5.15 |
| automatic-speech-recognition | FLEURS | Test WER (Hr) | 12.46 |
| automatic-speech-recognition | FLEURS | Test WER (Hu) | 15.72 |
| automatic-speech-recognition | FLEURS | Test WER (It) | 3 |
| automatic-speech-recognition | FLEURS | Test WER (Lt) | 20.35 |
| automatic-speech-recognition | FLEURS | Test WER (Lv) | 22.84 |
| automatic-speech-recognition | FLEURS | Test WER (Mt) | 20.46 |
Using it via the API
Once AxForge deploys nvidia-parakeet-tdt for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (nvidia-parakeet-tdt 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="nvidia-parakeet-tdt" -F file=@audio.mp3
Details
Languages
Trained / evaluated on
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 ↗