cohere-transcribe-03-2026
Coherefamily · Audiodocs.cohere.com/docs/models
Open source model focused on high-accuracy, multilingual speech transcription.
Updated 6 h ago · first seen 11 Sept 2026
model_01M294H99PYEJW44HFNM01GHD5
Overview
Identity
Identity block not returned by the API for this entity.
Openness
Openness not classified yet — no sourced evidence to place this model in the ontology.
Key facts
- Release date
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
- Status
Source:Cohere — docs & blogT1observed 12 h agohigh
- Official page
Source:Cohere — docs & blogT1observed 12 h agohigh
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
- API model id
Source:Cohere — docs & blogT1observed 12 h agohigh
Architecture
- Architecture
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
- Model type
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
- Parameters
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
- Weights dtype
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
- File size
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
- Library name
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
- Pipeline tag
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
- Hugging Face repo
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
Capabilities
Modalities
Modalities unavailable.
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
No capability flags have been observed from a source yet — we do not infer them.
- Languages
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
Hardware fit37
Assumptions (6)
- Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead.
- bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
- KV cache approximated at 0.5 GB per 8 192 tokens of context, independent of architecture (GQA/MLA models need less).
- A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
- Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
- Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
Lineage
Open in Graph →- descendant: cohere-transcribe-arabic-07-2026
Timeline1
Full timeline →Change history37
Viewing AI Atlas as of 12 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →Attributes as of 12 Sept 2026 30 claims in force
- Family
- Audio
- Release date
- 24 Mar 2026
- Status
- active
- Openness
- open-source
- License
- Apache-2.0
- Architecture
- CohereAsrForConditionalGeneration
- Parameters
- 2.07B
- Languages
- ar, de, el, en, es, fr, it, ja, ko, nl, pl, pt, vi, zh
- API model id
- cohere-transcribe-03-2026
- File size
- 4.1 GB
- Hugging Face repo
- CohereLabs/cohere-transcribe-03-2026
- Pipeline tag
- automatic-speech-recognition
- Official page
- Downloads
- 215,984
- Likes
- 1,115
- Commercial use allowed
- Yes
- Derivatives allowed
- Yes
- Endpoints
- Audio Transcriptions
- Gated
- auto
- Hf inference providers
- fal-ai
- Last modified
- 2026-06-10T15:46:19+00:00
- Library name
- transformers
- Downloads all time
- 3,311,170
- Model type
- cohere_asr
- Redistribution allowed
- Yes
- Tags
- transformers, safetensors, cohere_asr, automatic-speech-recognition, audio, hf-asr-leaderboard, speech-recognition, transcription, custom_code, ar, de, el, en, es, fr, it, ja, ko, nl, pl, pt, vi, zh
- Weights available
- Yes
- Weights dtype
- BF16
Familyfamily1
Release daterelease_date1
Statusstatus1
Opennessopenness12conflicting claims
Licenselicense1
Architecturearchitecture1
Parametersparameter_count1
Languageslanguages1
API model idapi_model_id1
File sizefile_size_gb1
Hugging Face repohf_repo1
Pipeline tagpipeline_tag1
Official pageofficial_url1
Model cardmodel_card_url1
Downloadsmetric.downloads1
Likesmetric.likes1
Descriptiondescription1
Endpointsendpoints1
Gatedgated1
Hf inference providershf_inference_providers1
Last modifiedlast_modified1
Library namelibrary_name1
Downloads all timemetric.downloads_all_time1
Model typemodel_type1
Weights dtypeweights_dtype1
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Provenance
Attributed facts
26
Source tiers
T1T27 / 19
Freshest observation
6 h ago
Conflicts
11 flagged
Source documents 4
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.
Data quality (62/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →