HF Model & Benchmark Matrix

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

Dolphin

JusperLee/Dolphin

kind
original
quant
bf16 (16-bit)
family
misc
modality
audio-to-audio
root model
—
provider
JusperLee
license
other
language
en
context
—
library
pytorch
vRAM (GB)
—
size on disk
—
downloads
2,971
likes
16
created
—
last modified
2026-07-22T09:50:19+00:00 (2026)
huggingface
https://huggingface.co/JusperLee/Dolphin
tags
pytorchsafetensorsdolphinaudio-visualspeech-separationcocktail-partymultimodallip-readingaudio-processingaudio-to-audiocustom_codeendataset:alibabasglab/VoxCeleb2-mixarxiv:2509.23610license:otherregion: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.