HF Model & Benchmark Matrix

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

spear-xlarge-speech-audio-v2

marcoyang/spear-xlarge-speech-audio-v2

kind
original
quant
bf16 (16-bit)
family
misc
modality
feature-extraction
root model
—
provider
marcoyang
license
apache-2.0
language
—
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
324
likes
4
created
—
last modified
2026-06-22T13:19:11+00:00 (2026)
huggingface
https://huggingface.co/marcoyang/spear-xlarge-speech-audio-v2
tags
transformerssafetensorsspearfeature-extractionhuggingfacespeechaudiospeech-representation-learningaudio-representation-learningself-supervised-learningautomatic-speech-recognitionaudio-taggingicml2026arxiv:2510.25955custom_codearxiv:2310.11230arxiv:2105.01051arxiv:2203.03022license:apache-2.0region:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr1.6low| LS960 | 1.6 | 2.9 |

Discussions (0)

none scraped.

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