bp500-base100k_voxpopuli

Home/Models/lgris/bp500-base100k_voxpopuli

lgris/bp500-base100k_voxpopuli

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: —
provider: lgris
license: apache-2.0
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 2,355
likes: 1
created: —
last modified: 2022-02-07T11:53:19+00:00 (2022)
huggingface: https://huggingface.co/lgris/bp500-base100k_voxpopuli
tags: transformerspytorchwav2vec2automatic-speech-recognitionaudiospeechptportuguese-speech-corpusPyTorchdataset:common_voicedataset:mlsdataset:cetucdataset:lapsbmdataset:voxforgedataset:tedxdataset:sidarxiv:2012.03411license:apache-2.0endpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
WER MLS	speech-asr	22.4		low	`\| bp\_500-base100k_voxpopuli (demonstration below) \| 0.142 \| 0.201 \| 0.052 \| 0.224 \| 0.102 \| 0.317 \| 0.048 \| 0.155 \|`
WER VoxPopuli	speech-asr	14.2	bp\_500-base100k_voxpopuli (demonstration below)	medium	`\| bp\_500-base100k_voxpopuli (demonstration below) \| 0.142 \| 0.201 \| 0.052 \| 0.224 \| 0.102 \| 0.317 \| 0.048 \| 0.155 \|`
WER VoxPopuli	speech-asr	9.9	bp\_500-base100k_voxpopuli + 4-gram (demonstration below)	medium	`\| bp\_500-base100k_voxpopuli + 4-gram (demonstration below) \| 0.099 \| 0.149 \| 0.047 \| 0.192 \| 0.115 \| 0.371 \| 0.127 \| 0.157 \|`
WER Common Voice	speech-asr	7.0		medium	`Common Voice 7.0`

none scraped.