HF Model & Benchmark Matrix

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

FireRedASR-AED-L

FireRedTeam/FireRedASR-AED-L

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
—
provider
FireRedTeam
license
apache-2.0
language
en, zh
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
265
likes
71
created
—
last modified
2025-03-05T11:45:32+00:00 (2025)
huggingface
https://huggingface.co/FireRedTeam/FireRedASR-AED-L
tags
audioautomatic-speech-recognitionasrenzharxiv:2501.14350license:apache-2.0region:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WER LibriSpeechspeech-asr1.93high| FireRedASR-AED | 4.48 | 1.93 | 4.44 |

Discussions (0)

none scraped.

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