Downloads · 30 days
4
10% of all-time downloads
shockz1/parakeet-tdt_ctc-110m-fp16-onnx
parakeet-tdt_ctc-110m-fp16-onnx is a automatic speech recognition model from shockz1. Use it when you need speech turned into text. It is set up for onnx. The card lists the license as cc-by-4.0.
Half-precision ONNX export of NVIDIA's parakeet-tdtctc-110m, packaged for in-browser speech recognition with onnxruntime-web on WebGPU.
Downloads · 30 days
4
10% of all-time downloads
All-time downloads
40
Public
Repo size
239 MB
Likes
0
Public
Click a slice to open those files.
.onnx239 MB · 100%
From the Hugging Face model README
Half-precision ONNX export of NVIDIA's parakeet-tdt_ctc-110m, packaged for
in-browser speech recognition with
onnxruntime-web on WebGPU.
Used by the subtitle tool in noupload — the weights are fetched once, cached in the browser, and every subsequent run is fully offline. No audio is ever uploaded anywhere.
| File | Size | Notes |
|---|---|---|
encoder-model.fp16.onnx | 229 MB | Conformer encoder, runs on WebGPU |
decoder_joint-model.fp16.onnx | 10.7 MB | TDT decoder + joint network |
vocab.txt | 10 KB | SentencePiece vocabulary (1025 tokens) |
config.json | — | 80 mel bins, subsampling 8 |
Single-file exports: no external .onnx_data, so a browser can load each one
with a single fetch.
import { ParakeetModel } from "parakeet.js";
const base = "https://huggingface.co/shockz1/parakeet-tdt_ctc-110m-fp16-onnx/resolve/main";
const model = await ParakeetModel.fromUrls({
encoderUrl: `${base}/encoder-model.fp16.onnx`,
decoderUrl: `${base}/decoder_joint-model.fp16.onnx`,
tokenizerUrl: `${base}/vocab.txt`,
backend: "webgpu-hybrid",
nMels: 80, // this model uses 80 mel bins, not the 128 of the 0.6B models
});
const { words } = await model.transcribe(pcm16kMono, 16000, { returnTimestamps: true });
Note: parakeet.js sizes the prediction network for the 0.6B models (2 layers).
This one has 1 layer, so read the real shape off joinerSession.inputMetadata
for input_states_1 and resize the initial decoder state accordingly.
Converted to fp16 from the fp32 ONNX export in
OpenVoiceOS/nvidia-parakeet-tdt_ctc-110m-onnx,
itself an export of
nvidia/parakeet-tdt_ctc-110m.
Licensed CC-BY-4.0, following the upstream model.