wav2vec2-large-xlsr-english (ONNX)

This is an ONNX version of BeebekBhz/wav2vec2-large-xlsr-english. It was automatically converted and uploaded using this Hugging Face Space.

Usage with Transformers.js

See the pipeline documentation for automatic-speech-recognition: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.AutomaticSpeechRecognitionPipeline

Fine-tuned XLSR-53 large model for speech recognition in English

Fine-tuned facebook/wav2vec2-large-xlsr-53 on English using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz.

Downloads last month: 3

Model tree for onnx-community/wav2vec2-large-xlsr-english-ONNX

Base model

BeebekBhz/wav2vec2-large-xlsr-english

Quantized

(1)

this model

Dataset used to train onnx-community/wav2vec2-large-xlsr-english-ONNX

Evaluation results

Test WER on Common Voice en
self-reported

19.060
Test CER on Common Voice en
self-reported

7.690
Test WER (+LM) on Common Voice en
self-reported

14.810
Test CER (+LM) on Common Voice en
self-reported

6.840
Dev WER on Robust Speech Event - Dev Data
self-reported

27.720
Dev CER on Robust Speech Event - Dev Data
self-reported

11.650
Dev WER (+LM) on Robust Speech Event - Dev Data
self-reported

20.850
Dev CER (+LM) on Robust Speech Event - Dev Data
self-reported

11.010