Xenova/wav2vec2-bert-CV16-en
By Xenova · ↓ 16 · ♥ 0 · Updated 2025-08-18
What's in this repo
This page lists the files in Xenova/wav2vec2-bert-CV16-en, including model.onnx, model_bnb4.onnx, model_fp16.onnx and more.
- 7 ONNX models (.onnx files)
- 17 files, including 7 .json, 7 .onnx, 1 .md, 1 .onnx_data
- Last updated 2025-08-18
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/model.onnx | — | Download |
| onnx/model_bnb4.onnx | — | Download |
| onnx/model_fp16.onnx | — | Download |
| onnx/model_q4.onnx | — | Download |
| onnx/model_q4f16.onnx | — | Download |
| onnx/model_quantized.onnx | — | Download |
| onnx/model_uint8.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
https://huggingface.co/hf-audio/wav2vec2-bert-CV16-en with ONNX weights to be compatible with Transformers.js.
Usage (Transformers.js)
If you haven't already, you can install the Transformers.js JavaScript library from NPM using:
npm i @huggingface/transformers
You can then use the model for speech recognition with:
import { pipeline } from '@huggingface/transformers';
// Create an Automatic Speech Recognition pipeline
const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/wav2vec2-bert-CV16-en');
// Transcribe audio
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';
const output = await transcriber(url);
// { text: 'and so my fellow americans ask not what your country can do for you ask what you can do for your country' }
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).
Model info
Created: 2024-01-26
Updated: 2025-08-18
View on Hugging Face