Model reference · open weights
cohere-transcribe-03-2026 is an open-weight audio or speech model from handy-computer, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
cohere-transcribe-03-2026: transcribe.cpp GGUF GGUF conversions of CohereLabs/cohere-transcribe-03-2026 for use with transcribe.cpp. Ported from upstream commit 76b8b23, pinned 2026-04-16. Validated against the Transformers reference at transcribe.cpp commit bf0d0b7 on 2026-04-18. Offline multilingual speech-to-text covering 14 languages (English, French, German, Spanish, Italian, Portuguese, Dutch, Polish, Greek, Arabic, Japanese, Chinese, Vietnamese, Korean). A Conformer encoder with a Transformer encoder-decoder head (cross-attention, tied token embedding). Takes a 16 kHz mono WAV and produces a transcript. Decoding is autoregressive. Downloads WER measured on the full LibriSpeech test-clean split (2620 utterances) with greedy decoding and no external LM. BF16 reference baseline: 1.26%. Cohere's self-reported number on the same split is 1.25% (Open ASR Leaderboard, as of 2026-03-26). Both ours and Cohere's numbers use the Whisper EnglishTextNormalizer, so the comparison is apples-to-apples and our port matches the upstream reference within rounding. Usage Build transcribe.cpp from source: Run on a 16 kHz mono WAV: If your audio isn't already 16 kHz mono WAV, convert it first: See the transcribe.cpp model page for performance numbers, numerical validation, and reproduction steps. License Inherited from the base model: Apache-2.0. See the upstream model card for full terms. Original Model Card The section below is reproduced from CohereLabs/cohere-transcribe-03-2026 at commit 76b8b23 for offline reference. The upstream card is the authoritative source. Cohere Transcribe Cohere Transcribe is an open source release of a 2B parameter dedicated audio-in, text-out automatic speech recognition (ASR) model. The model supports 14 languages. Developed by: Cohere and Cohere Labs. Point of Contact: Cohere Labs. @scope { th, td { text-align: left; padding: 0.375rem 0.625rem; letter-spacing: 0; vertical-align: top; line-height: 133.3333%; border: 1px solid #e0e0e0; } ul { list-style-type: disc; margin: 0; padding-left: 1em; li { margin: 0.25rem 0 0; line-height: 133.3333%; } } } Trained on 14 languages: Dutch, Polish</li ✨Try the Cohere Transcribe demo✨ Usage Cohere Transcr
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | handy-computer |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | transcribe.cpp |
| Based on | CohereLabs/cohere-transcribe-03-2026 |
| Released | 2026-04-15 |
| Popularity | 970k downloads / month |
| Likes | 3 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| cohere-transcribe-03-2026-gguf | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys cohere-transcribe-03-2026 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (cohere-transcribe-03-2026 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="cohere-transcribe-03-2026" -F file=@audio.mp3
Details
Languages
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗