wav2vec2-large-xlsr-53-japanese

Home/Models/jonatasgrosman/wav2vec2-large-xlsr-53-japanese

jonatasgrosman/wav2vec2-large-xlsr-53-japanese

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: jonatasgrosman/wav2vec2-large-xlsr-53-japanese
provider: jonatasgrosman
license: apache-2.0
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 1,787,375
likes: 62
created: —
last modified: 2022-12-14T01:58:09+00:00 (2022)
huggingface: https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-japanese
tags: transformerspytorchjaxwav2vec2automatic-speech-recognitionaudiospeechxlsr-fine-tuning-weekjadataset:common_voicedoi:10.57967/hf/3568license:apache-2.0model-indexendpoints_compatibleregion:usdeploy:azure

benchmark	category	score	conf	evidence
WER	speech-asr	81.8	high	`\| jonatasgrosman/wav2vec2-large-xlsr-53-japanese \| 81.80% \| 20.16% \|`
CER	speech-asr	20.16	high	`\| jonatasgrosman/wav2vec2-large-xlsr-53-japanese \| 81.80% \| 20.16% \|`
WER Common Voice	speech-asr	6.1	medium	`Common Voice 6.1`

none scraped.