wav2vec2-large-100k-voxpopuli-catala

Home/Models/ccoreilly/wav2vec2-large-100k-voxpopuli-catala

ccoreilly/wav2vec2-large-100k-voxpopuli-catala

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: —
provider: ccoreilly
license: apache-2.0
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 310
likes: 2
created: —
last modified: 2022-02-08T00:59:52+00:00 (2022)
huggingface: https://huggingface.co/ccoreilly/wav2vec2-large-100k-voxpopuli-catala
tags: transformerspytorchjaxwav2vec2automatic-speech-recognitionaudiospeechspeech-to-textcadataset:common_voicedataset:parlament_parlalicense:apache-2.0model-indexendpoints_compatibleregion:usdeploy:azure

benchmark	category	score	context	conf	evidence
WER Common Voice	speech-asr	6.1		medium	`CommonVoice 6.1`
WER	speech-asr	5.98		low	`\| [Test split CV+ParlamentParla]((https://github.com/ccoreilly/wav2vec2-catala/blob/master/test-filtered.csv)) \| 5.98% \|`

none scraped.