Cohere Transcribe 03-2026

Dedicated 2B ASR for 14-language transcription

MultilingualApache-2.0
Desktop app Open the Models screen and click install.
CLI
$ openasr pull cohere-transcribe-03-2026:q8
Download .oasr

Overview

Cohere Transcribe 03-2026 is Cohere and Cohere Labs' open release of a 2B-parameter automatic speech recognition model. It is a dedicated audio-in, text-out architecture with a Conformer-based acoustic encoder and a lightweight Transformer decoder, trained from scratch for transcription. The upstream model card lists support for 14 languages across English, European, APAC, and MENA coverage and reports Apache-2.0 licensing. This OpenASR repo repackages the original CohereLabs/cohere-transcribe-03-2026 weights as .oasr packs that run natively in the OpenASR runtime with no Python at inference time. For most users the q8_0 build is the recommended default; q4_k is for tighter memory budgets and fp16 is for verification or maximum fidelity.

Highlights

  • 🎙️ Dedicated ASR — audio-in, text-out model built specifically for transcription
  • 🌍 14 languages — covers English, major European languages, Arabic, Chinese, Japanese, Korean, and Vietnamese
  • 🧱 Conformer encoder-decoder — large acoustic encoder with a lightweight Transformer decoder
  • 🦀 Native in OpenASR.oasr packs run with no Python at inference, engineered for CPU and Apple Silicon

Tags

Pull stringSizeQuantJFK ΔWER
cohere-transcribe-03-2026:fp16 3.9 GB fp16 0%
cohere-transcribe-03-2026:q8default 2.3 GB q8_0 0%
cohere-transcribe-03-2026:q4 1.4 GB q4_k 0%

Usage

These are CLI / local-server examples. The desktop app runs this model without typing a command — see the desktop install path above.

bash · transcribe a file
$ openasr pull cohere-transcribe-03-2026:q8
↓ cohere-transcribe-03-2026.oasr  2.3 GB  ✓ verified sha256
$ openasr transcribe meeting.wav --backend native --model-pack ~/.openasr/models/cohere-transcribe-03-2026/q8_0/cohere-transcribe-03-2026-q8_0.oasr
✓ local transcript · 0 bytes sent
bash · serve a local API
$ openasr serve --backend native --model-pack ~/.openasr/models/cohere-transcribe-03-2026/q8_0/cohere-transcribe-03-2026-q8_0.oasr --addr 127.0.0.1:8080
▶ http://127.0.0.1:8080 · model=cohere-transcribe-03-2026 · 0 bytes will leave this host
python · client.py
from openai import OpenAI
client = OpenAI(base_url="http://127.0.0.1:8080/v1", api_key="local")
audio = open("meeting.wav", "rb")
text = client.audio.transcriptions.create(model="cohere-transcribe-03-2026", file=audio)

Other models