ae9is/parakeet-tdt-0.6b-v3-onnx
By ae9is · ↓ 0 · ♥ 0 · Updated 2026-03-22
What's in this repo
This page lists the files in ae9is/parakeet-tdt-0.6b-v3-onnx, including decoder_model_merged.onnx, decoder_model_merged_int8.onnx, encoder_model.onnx and more.
- 5 ONNX models (.onnx files)
- 14 files, including 5 .json, 5 .onnx, 1 .md, 1 .data, 1 .txt
- Last updated 2026-03-22
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/decoder_model_merged.onnx | — | Download |
| onnx/decoder_model_merged_int8.onnx | — | Download |
| onnx/encoder_model.onnx | — | Download |
| onnx/encoder_model_int8.onnx | — | Download |
| onnx/nemo128.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
NVIDIA Parakeet TDT 0.6B V3 (Multilingual) model converted to ONNX format for onnx-asr, and then some configuration changed for Transformers.js.
Important: The following example requires a custom version of Transformers.js here.
const model = 'ae9is/parakeet-tdt-0.6b-v3-onnx'
let transcriber = await pipeline('automatic-speech-recognition', model)
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/french-audio.wav'
let audioData = await loadAudio(url)
// Transcribe French
let output = await transcriber(audioData, { language: 'french', task: 'transcribe' })
const expected = " J'adore, j'aime, je n'aime pas, je déteste."
console.log('output', output?.text)
console.log('expected', expected)
await transcriber.dispose()
Model info
Created: 2026-03-22
Updated: 2026-03-22
View on Hugging FaceFiles (14)
Related models
More from ae9is
No other models by this author.