HF Model & Benchmark Matrix

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

cohere-transcribe-arabic-07-2026-int8

NAMAA-Space/cohere-transcribe-arabic-07-2026-int8

kind
bnb-4bit
quant
4bit
family
command
modality
automatic-speech-recognition
root model
CohereLabs/cohere-transcribe-arabic-07-2026
provider
NAMAA-Space
license
apache-2.0
language
ar, en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
278
likes
2
created
—
last modified
2026-07-10T20:10:34+00:00 (2026)
huggingface
https://huggingface.co/NAMAA-Space/cohere-transcribe-arabic-07-2026-int8
tags
transformerssafetensorscohere_asrautomatic-speech-recognitionarabicsaudi-dialectquantizedbitsandbytesarenbase_model:CohereLabs/cohere-transcribe-arabic-07-2026base_model:quantized:CohereLabs/cohere-transcribe-arabic-07-2026license:apache-2.0endpoints_compatible8-bitregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr46.0low| **This model (INT8)** | **2.35 GB** | **0.46%** |

Discussions (0)

none scraped.

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