AxForge
Sign in Get started

Model reference · open weights

cohere-transcribe-arabic-07-2026

Audio CohereLabs Speech→text 1 build Open weights 54k dl/mo

cohere-transcribe-arabic-07-2026 is an open-weight audio or speech model from Cohere. cohere-transcribe-arabic-07-2026 (BF16) weighs 4.1 GB; the smallest configuration that runs it is RTX 3060 12 GB.

  • Cohere Transcribe Arabic is a 2.1B parameter open-source model for automatic speech recognition, designed to transcribe Arabic, English, and code-switched audio.
  • It utilizes a Conformer encoder-decoder architecture and is released under the Apache 2.0 license.
  • The model supports native integration with Transformers and vLLM for offline and online inference.

Summary of the CohereLabs/cohere-transcribe-arabic-07-2026 model card, 2026-10-01

Hugging Face ↗GitHub ↗

What it is

Released byCohere
Released2026-06-18
Parameters2.1B
VRAM4.1 GB for the weights

What it runs on

Memory and cards for cohere-transcribe-arabic-07-2026 (BF16)

4.1 GBweights, file size
1.6 GBruntime overhead
CardOne streamMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms