HF Model & Benchmark Matrix

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

cohere-transcribe-arabic-07-2026-dialectal

oddadmix/cohere-transcribe-arabic-07-2026-dialectal

kind
original
quant
bf16 (16-bit)
family
command
modality
automatic-speech-recognition
root model
CohereLabs/cohere-transcribe-arabic-07-2026
provider
oddadmix
license
apache-2.0
language
—
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
339
likes
1
created
—
last modified
2026-07-09T23:34:50+00:00 (2026)
huggingface
https://huggingface.co/oddadmix/cohere-transcribe-arabic-07-2026-dialectal
tags
transformerssafetensorscohere_asrautomatic-speech-recognitionarabicdialectal-arabicasrardataset:oddadmix/dialectal-arabic-lahgtna-v2-smaller-augmentedbase_model:CohereLabs/cohere-transcribe-arabic-07-2026base_model:finetune:CohereLabs/cohere-transcribe-arabic-07-2026license:apache-2.0model-indexendpoints_compatibleregion:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr59.0Zero-shot WERlow| **whisper-large-v3-turbo** 🏆 | 809M | 0.590 | **0.344** | 0.115 |
WERspeech-asr34.4mediumWER 0.344
CERspeech-asr17.4low| Base (cohere-transcribe-arabic, zero-shot) | 0.457 | 0.174 |
CERspeech-asr11.5Zero-shot WERlow| **whisper-large-v3-turbo** 🏆 | 809M | 0.590 | **0.344** | 0.115 |

Discussions (0)

none scraped.

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