NEWVectors or files. Pick a path.Start →
    Models/Speech & Audio/nvidia/parakeet-ctc-1.1b
    NeMoTranscriptioncc-by-4.0

    parakeet-ctc-1.1b

    by nvidia

    Fast Conformer CTC model for high-throughput English speech recognition

    1.0Mdl/month
    51likes
    1.1Bparams
    Identifiers
    Model ID
    nvidia/parakeet-ctc-1.1b
    Feature URI
    mixpeek://transcription@v1/nvidia_parakeet_ctc_1b_v1

    Overview

    Parakeet CTC 1.1B is NVIDIA's XXL Fast Conformer model with a CTC decoder, trained on 64K hours of English speech. The convolutional-transformer hybrid architecture processes audio up to 11 hours in a single pass on an A100 80GB GPU, achieving a real-time factor of 1,336x (1,336 hours of audio transcribed per hour of compute).

    On Mixpeek, Parakeet CTC powers high-throughput English transcription for large audio and video libraries where speed matters. Its non-autoregressive CTC decoding enables massive parallelism, making it ideal for batch processing millions of hours of content.

    Architecture

    Fast Conformer encoder (CNN + Transformer hybrid) with 1.1B parameters and CTC (Connectionist Temporal Classification) decoder. Processes 80-channel log-mel spectrograms. Supports local attention for processing audio segments up to 11 hours on A100 80GB.

    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: "nvidia/parakeet-ctc-1.1b" },
      },
    });

    Capabilities

    • 1,336x real-time transcription speed
    • Processes up to 11 hours of audio in a single pass
    • Low WER on standard English benchmarks
    • Non-autoregressive CTC decoding for parallel inference
    • Greedy decoding without external language model

    Use Cases on Mixpeek

    Batch transcription of massive audio/video archives at scale
    High-throughput English speech search across media libraries
    Podcast and broadcast indexing where speed is critical

    Benchmarks

    DatasetMetricScoreSource
    LibriSpeech test-cleanWER1.83%NVIDIA, 2024: Parakeet model card
    AMI Meeting CorpusWER15.62%NVIDIA, 2024: Parakeet model card

    Performance

    Input Size16kHz audio, up to 11 hours per pass
    GPU LatencyRTFx ~1,336 (A100 80GB)
    GPU Throughput~1,336 hours audio / hour compute (A100)
    GPU Memory~4.2 GB

    Non-autoregressive CTC decoder enables massive batch parallelism

    Specification

    FrameworkNeMo
    Organizationnvidia
    FeatureTranscription
    Outputtext + timestamps
    Modalitiesvideo, audio
    RetrieverTranscript Search
    Parameters1.1B
    Licensecc-by-4.0
    Downloads/mo1.0M
    Likes51

    Build a pipeline with parakeet-ctc-1.1b

    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