HF Model & Benchmark Matrix

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

audio-flamingo-3-hf

nvidia/audio-flamingo-3-hf

kind
original
quant
bf16 (16-bit)
family
misc
modality
audio-text-to-text
root model
nvidia/audio-flamingo-3-hf
provider
nvidia
license
other
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
197,695
likes
189
created
—
last modified
2026-04-13T08:08:11+00:00 (2026)
huggingface
https://huggingface.co/nvidia/audio-flamingo-3-hf
tags
transformerssafetensorsaudioflamingo3text2text-generationaudioreasoningaudio understandingASRaudio-text-to-textendataset:nvidia/AudioSkillsdataset:nvidia/AF-Chatdataset:nvidia/AF-Thinkdataset:nvidia/LongAudioarxiv:2507.08128arxiv:2505.13032license:otherendpoints_compatibleregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr15.0mediumCommon Voice 15

Discussions (0)

none scraped.

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