NEWVectors or files. Pick a path.Start →
    Models/Speech & Audio/Qwen/Qwen3-ASR-0.6B
    HFTranscriptionapache-2.0

    Qwen3-ASR-0.6B

    by Qwen

    Ultra-fast 0.6B ASR model supporting 52 languages with 92ms time-to-first-token

    1.2Mdl/month
    317likes
    938Mparams
    Identifiers
    Model ID
    Qwen/Qwen3-ASR-0.6B
    Feature URI
    mixpeek://transcription@v1/qwen3_asr_06b_v1

    Overview

    Qwen3-ASR-0.6B is a compact automatic speech recognition model supporting 52 languages and dialects. It achieves 92ms average time-to-first-token, making it suitable for real-time transcription. At high concurrency (128), it can process 2000 seconds of speech per second, making it one of the fastest open ASR models available.

    Architecture

    Encoder-decoder architecture with a Conformer-based audio encoder and a Qwen3 0.6B decoder. The audio encoder processes mel-spectrogram features through conformer blocks with relative positional encoding, while the decoder generates text tokens autoregressively with cross-attention to encoder states.

    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: "s3",
        version: "v1",
        parameters: { model_id: "mixpeek://transcription@v1/qwen3_asr_06b_v1" },
      },
    });

    Capabilities

    • Multilingual ASR (52 languages)
    • Real-time streaming transcription
    • High-concurrency batch processing
    • Low-latency first-token generation

    Use Cases on Mixpeek

    Real-time meeting transcription
    Call center speech analytics
    Multilingual podcast transcription
    Edge device speech-to-text

    Benchmarks

    DatasetMetricScoreSource
    LibriSpeech (test-clean)WER2.8Model card
    CommonVoice (en)WER8.1Model card

    Performance

    Input SizeVariable
    GPU Latency92ms time-to-first-token
    GPU Throughput2000s speech/sec at concurrency 128
    GPU MemoryModel dependent

    Specification

    FrameworkHF
    OrganizationQwen
    FeatureTranscription
    Outputtext + timestamps
    Modalitiesvideo, audio
    RetrieverTranscript Search
    Parameters938M
    Licenseapache-2.0
    Downloads/mo1.2M
    Likes317

    Research Paper

    Model paper or technical report

    arxiv.org

    Build a pipeline with Qwen3-ASR-0.6B

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

    Run it on your own data, free