HF Model & Benchmark Matrix

higgs-audio-v2-generation-3B-base

szhengac25/higgs-audio-v2-generation-3B-base

kind

original

quant

bf16 (16-bit)

family

misc

modality

text-to-speech

root model

bosonai/higgs-audio-v2-generation-3B-base

provider

szhengac25

license

—

language

—

context

—

library

—

vRAM (GB)

—

size on disk

—

downloads

9

likes

1

created

—

last modified

2025-08-29T21:50:11+00:00 (2025)

huggingface

https://huggingface.co/szhengac25/higgs-audio-v2-generation-3B-base

tags

safetensorshiggs_audiotext-to-speechenzhdekoarxiv:2505.23009license:otherregion:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (0)

none scraped.