HF Model & Benchmark Matrix

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

kb-whisper-large

KBLab/kb-whisper-large

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
openai/whisper-large-v3
provider
KBLab
license
apache-2.0
language
sv
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
7,637
likes
64
created
—
last modified
2025-08-27T12:35:05+00:00 (2025)
huggingface
https://huggingface.co/KBLab/kb-whisper-large
tags
transformersonnxsafetensorswhisperautomatic-speech-recognitionctranslate2svdataset:KBLab/rixvox-v2arxiv:2505.17538base_model:openai/whisper-large-v3base_model:quantized:openai/whisper-large-v3license:apache-2.0endpoints_compatibleregion:usdeploy:azure

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr67.8high| | OpenAI | 59.2 | 67.8 | 85.2 |
WER FLEURSspeech-asr59.2high| | OpenAI | 59.2 | 67.8 | 85.2 |

Discussions (0)

none scraped.

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