HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

wav2vec2-base-it-latin

lsb/wav2vec2-base-it-latin

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
facebook/wav2vec2-base
provider
lsb
license
agpl-3.0
language
la
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
197
likes
1
created
—
last modified
2022-03-24T11:51:21+00:00 (2022)
huggingface
https://huggingface.co/lsb/wav2vec2-base-it-latin
tags
transformerspytorchwav2vec2automatic-speech-recognitionrobust-speech-eventhf-asr-leaderboardladataset:lsb/poetaexmachina-mp3-recitationslicense:agpl-3.0model-indexendpoints_compatibleregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr39.8mediumWER: 0.398

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.