whisper-large-v3-turbo
by openai
Whisper at 216x real-time -- pruned decoder for production-grade ASR speed
openai/whisper-large-v3-turbomixpeek://transcription@v1/openai_whisper_large_v3_turboOverview
Whisper Large V3 Turbo is OpenAI's speed-optimized variant of Whisper Large V3, achieved by pruning the decoder from 32 layers to 4. This yields a 216x real-time speed factor with less than 1% increase in word error rate compared to the full model.
The model retains the full encoder and multilingual capabilities of Whisper Large V3, supporting 100+ languages. On Mixpeek, it provides the best speed/quality tradeoff for production ASR workloads -- fast enough for batch processing of large video libraries while maintaining near-full accuracy.
Architecture
Encoder-decoder Transformer. Full Whisper Large V3 encoder (32 layers) with pruned decoder (4 layers, down from 32). 809M total parameters. 128 mel spectrogram input. Multilingual, multitask (transcription + translation).
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: "openai/whisper-large-v3-turbo" },
},
});Capabilities
- 216x real-time speed factor
- 100+ language transcription
- Speech translation to English
- Timestamp prediction
- Near-identical accuracy to full Whisper Large V3
Use Cases on Mixpeek
Benchmarks
| Dataset | Metric | Score | Source |
|---|---|---|---|
| LibriSpeech Clean | WER | 2.0% | OpenAI, 2024 -- Model Card |
| CommonVoice 15 (multilingual) | WER | 11.7% | OpenAI, 2024 -- Model Card |
Performance
Common Pipeline Companions
Explore on Mixpeek
Compare alternatives in this category
Hand-picked tools & platforms compared
Deep-dive technical guide
See how Mixpeek runs models as extractors
Store & search embeddings at scale
Usage-based pricing for pipelines
Compare models, APIs & infrastructure
Specification
Research Paper
Whisper Large V3 Turbo
arxiv.orgBuild a pipeline with whisper-large-v3-turbo
Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.
Open Studio