Marketplace · Speech-to-text
istupakov/parakeet-tdt-0.6b-v3-onnx
Call istupakov/parakeet-tdt-0.6b-v3-onnx through one OpenAI-compatible API. It's served by 1 host on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.
At a glance.
multilingual
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
api_key=INPHERIO_API_KEY)
text = client.audio.transcriptions.create(
model="istupakov/parakeet-tdt-0.6b-v3-onnx",
file=open("audio.mp3", "rb"),
)istupakov/parakeet-tdt-0.6b-v3-onnx in detail.
NVIDIA Parakeet TDT 0.6B V3 (Multilingual) [model](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) converted to ONNX format for [onnx-asr](https://github.com/istupakov/onnx-asr).
- Published by
- istupakov
- Parameters
- 600M
- Download size
- 652 MB (weights on Hugging Face)
- Architecture
- nemo-conformer-tdt
- Licence
- CC BY 4.0
- Based on
- nvidia/parakeet-tdt-0.6b-v3
- Task
- automatic speech recognition
- Languages
- en, es, fr, de, bg, hr, cs, da, nl, et, fi, el
- First published
- 16 Aug 2025
- Last updated
- 17 Feb 2026
- Downloads (30 days)
- 121,361 on Hugging Face
- Likes
- 70
onnx nemo-conformer-tdt automatic-speech-recognition asr onnx-asr en es fr de bg hr cs da nl et fi
The model card
Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.
NVIDIA Parakeet TDT 0.6B V3 (Multilingual) model converted to ONNX format for onnx-asr.
Install onnx-asr
pip install onnx-asr[cpu,hub]
Load Parakeet TDT model and recognize wav file
import onnx_asr
model = onnx_asr.load_model("nemo-parakeet-tdt-0.6b-v3")
print(model.recognize("test.wav"))
Code for models export
import nemo.collections.asr as nemo_asr
from pathlib import Path
model = nemo_asr.models.ASRModel.from_pretrained("nvidia/parakeet-tdt-0.6b-v3")
onnx_dir = Path("nemo-onnx")
onnx_dir.mkdir(exist_ok=True)
model.export(str(Path(onnx_dir, "model.onnx")))
with Path(onnx_dir, "vocab.txt").open("wt") as f:
for i, token in enumerate([*model.tokenizer.vocab, ""]):
f.write(f"{token} {i}\n")Sources: istupakov/parakeet-tdt-0.6b-v3-onnx on Hugging Face. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.
Who's serving it.
Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.
| Host | Tier | Price | Measured speed | Health | State | Rent |
|---|---|---|---|---|---|---|
| GTX 1080 Ti (11G) | L1 | £0.03 /h audio | 1.9× real time | 78 | loaded | £0.60/h |
Live data, refreshed on every visit. How billing works.
Room on the grid for your machine.
Right now one machine serves istupakov/parakeet-tdt-0.6b-v3-onnx. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.
Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load istupakov/parakeet-tdt-0.6b-v3-onnx, and the platform benchmarks it on your hardware before your first request.