NEWVectors or files. Pick a path.Start →
    Models/Speech & Audio/CohereLabs/cohere-transcribe-arabic-07-2026
    HFTranscriptionapache-2.0

    cohere-transcribe-arabic-07-2026

    by CohereLabs

    Dialect-aware Arabic ASR with Arabic-English code-switching

    6Kdl/month
    81likes
    2.1Bparams
    Identifiers
    Model ID
    CohereLabs/cohere-transcribe-arabic-07-2026
    Feature URI
    mixpeek://transcription@v1/cohere_transcribe_arabic_v1

    Overview

    Cohere Transcribe Arabic is a 2B-parameter speech recognition model from Cohere Labs (July 2026) built specifically for Arabic — including regional dialects and Arabic-English code-switching, the two places general-purpose ASR models degrade hardest. On the Open Universal Arabic ASR Leaderboard it averages 25.87% WER across dialect-heavy test sets, with 5.82% WER on Common Voice Arabic.

    On Mixpeek, it fills the Arabic gap in transcription pipelines: Arabic broadcast media, Gulf and Levantine dialect recordings, and mixed Arabic-English business audio become searchable text indexed alongside embeddings and faces. Pair it with voice-activity detection at ingest — the model transcribes non-speech sounds without it and does not emit timestamps or speaker labels on its own.

    Architecture

    Conformer-based encoder-decoder: a large Conformer encoder for acoustic representations with a lightweight Transformer decoder for token generation. Audio resampled to 16kHz. No built-in language detection, timestamps, or diarization. Apache 2.0 license.

    Mixpeek SDK Integration

    import { Mixpeek } from "mixpeek";
    
    const mx = new Mixpeek({ apiKey: "API_KEY" });
    
    // Managed: create a collection over a bucket; Mixpeek runs this model's extractor
    const collection = await mx.collections.create({
      namespace_id: "my-namespace",
      collection_name: "my-collection",
      source: { type: "bucket", bucket_ids: ["bkt_your_bucket"] },
      feature_extractor: {
        feature_extractor_name: "transcription",
        version: "v1",
        parameters: { model_id: "CohereLabs/cohere-transcribe-arabic-07-2026" },
      },
    });

    Capabilities

    • Arabic dialect coverage (Gulf, Levantine, Egyptian, Maghrebi test sets)
    • Arabic-English code-switching
    • 5.82% WER on Common Voice Arabic; 15.54% WER on MGB-2 broadcast
    • 25.87% average WER on the Open Universal Arabic ASR Leaderboard
    • Compact 2B parameters under Apache 2.0

    Use Cases on Mixpeek

    Arabic broadcast media: make news and talk-show archives searchable
    Regional dialect content: transcribe Gulf, Levantine, and Egyptian recordings
    Business audio: handle Arabic-English code-switched meetings and calls
    MENA media libraries: index Arabic speech next to visual and text features

    Benchmarks

    DatasetMetricScoreSource
    Open Universal Arabic ASR Leaderboard (avg)WER25.87%Cohere Labs, 2026 — Model Card
    Common Voice (Arabic)WER5.82%Cohere Labs, 2026 — Model Card
    MGB-2 (broadcast)WER15.54%Cohere Labs, 2026 — Model Card
    MASC (clean)WER19.60%Cohere Labs, 2026 — Model Card

    Specification

    FrameworkHF
    OrganizationCohereLabs
    FeatureTranscription
    Outputtext + timestamps
    Modalitiesvideo, audio
    RetrieverTranscript Search
    Parameters2.1B
    Licenseapache-2.0
    Downloads/mo6K
    Likes81

    Research Paper

    Cohere Transcribe Arabic Model Card

    arxiv.org

    Build a pipeline with cohere-transcribe-arabic-07-2026

    Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

    Run on your data, free