HF Model & Benchmark Matrix

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

acestep-captioner

ACE-Step/acestep-captioner

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-to-audio
root model
—
provider
ACE-Step
license
mit
language
—
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
27,443
likes
64
created
—
last modified
2026-02-03T06:33:55+00:00 (2026)
huggingface
https://huggingface.co/ACE-Step/acestep-captioner
tags
transformerssafetensorsqwen2_5_omnitext-to-audiomusicaudioarxiv:2602.00744license:mitendpoints_compatibleregion:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (0)

none scraped.

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