cohere-transcribe-arabic-07-2026
Coherefamily · Audiodocs.cohere.com/docs/models
Finetune optimized for Arabic audio inputs
Updated 4 h ago · first seen 11 Sept 2026
model_01M294H99YT5GCHS2VEGK95FP5
Overview
Identity
- Canonical model
- Yesidentity confidence: highOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
- Official checkpoints
- official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
- Artifacts
- None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
- Provider deployments
- None recorded
- API aliases
- cohere-transcribe-arabic-07-2026Identifiers under which providers and evaluators refer to this model.
- Folded evaluation variants
- 0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.
Openness
Open weights— weights downloadable under Apache-2.0; commercial use allowed; redistribution allowed; derivatives allowed; 4 dimensions unknown.
Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.
Weights
Yes
Inference code
—
Training code
—
Training data
—
Dataset
—
Commercial use
Yes
Redistribution
Yes
Derivatives
Yes
Licence: Apache License 2.0 (permissive · SPDX Apache-2.0 · stated as “apache-2.0”)
dimensions marked null are unknown, not false
Key facts
- Release date
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Status
Source:Cohere — docs & blogT1observed 5 d agohigh
- Official page
Source:Cohere — docs & blogT1observed 5 d agohigh
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- API model id
Source:Cohere — docs & blogT1observed 5 d agohigh
Architecture
- Architecture
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Model type
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Parameters
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Weights dtype
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- File size
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Library name
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Pipeline tag
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Hugging Face repo
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
Capabilities
Modalities
- Modalities
- audiotext
- Input
- audio
- Output
- text
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 5 d agomedium
Hardware fit37
Assumptions (7)
- Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
- bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
- KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), 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).
- Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.
Lineage
Open in Graph →- ancestor: cohere-transcribe-03-2026
Versions & Artifacts0
Version history
Openness1 change
11 Sept 2026→12 Sept 2026current
Licensefirst observation only
11 Sept 2026current
Parametersfirst observation only
11 Sept 2026current
Statusfirst observation only
11 Sept 2026current
Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.
Artifacts 0
No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.
Change history49
Viewing AI Atlas as of 15 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →Attributes as of 15 Sept 2026 37 claims in force
- Family
- Audio
- Release date
- 18 Jun 2026
- Status
- active
- Openness
- open-weights
- License
- Apache-2.0
- Architecture
- CohereAsrForConditionalGeneration
- Parameters
- 2.07B
- Modalities
- audio, text
- Input modalities
- audio
- Output modalities
- text
- Languages
- ar, en
- API model id
- cohere-transcribe-arabic-07-2026
- Base model
- CohereLabs/cohere-transcribe-03-2026
- File size
- 4.1 GB
- Hugging Face repo
- CohereLabs/cohere-transcribe-arabic-07-2026
- Pipeline tag
- automatic-speech-recognition
- Official page
- Downloads
- 46,904
- Likes
- 189
- Access
- gated
- Commercial use allowed
- Yes
- Derivatives allowed
- Yes
- Endpoints
- Audio Transcriptions
- Gated
- auto
- Gated mode
- auto
- Last modified
- 2026-07-13T16:11:20+00:00
- Library name
- transformers
- License key
- Apache-2.0
- License raw
- apache-2.0
- Downloads all time
- 122,526
- Model type
- cohere_asr
- Redistribution allowed
- Yes
- Tags
- transformers, safetensors, cohere_asr, automatic-speech-recognition, audio, speech-recognition, transcription, arabic, asr, arabic-asr, arabic-dialect, arabic-speech-recognition, ar, en
- Weights available
- Yes
- Weights dtype
- BF16
Familyfamily1
Release daterelease_date1
Statusstatus1
Opennessopenness2
Licenselicense1
Architecturearchitecture1
Parametersparameter_count1
Modalitiesmodalities1
Input modalitiesmodalities_input1
Output modalitiesmodalities_output1
Languageslanguages1
API model idapi_model_id1
Base modelbase_model1
File sizefile_size_gb1
Hugging Face repohf_repo1
Pipeline tagpipeline_tag1
Official pageofficial_url1
Model cardmodel_card_url1
Downloadsmetric.downloads6
Likesmetric.likes2
Accessaccess1
Commercial use allowedcommercial_use_allowed1
Derivatives allowedderivatives_allowed1
Descriptiondescription1
Endpointsendpoints1
Gatedgated1
Gated modegated_mode1
Last modifiedlast_modified1
Library namelibrary_name1
License keylicense_key1
License rawlicense_raw1
Downloads all timemetric.downloads_all_time6
Model typemodel_type1
Redistribution allowedredistribution_allowed1
Weights availableweights_available1
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
37
Source tiers
T1T26 / 31
Freshest observation
5 h ago
Conflicts
None
Source documents 3
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.
Data quality (73/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →