Whisper Large v3 (ONNX)

Production-ready ONNX conversion of openai/whisper-large-v3 for high-quality multilingual speech recognition — converted for edge deployment via Edgework.ai.

Highlights

  • Best-in-class multilingual ASR — OpenAI's flagship speech model
  • 1.5B parameters — maximum quality for 99+ languages
  • Trained on 1M+ hours of weakly-supervised audio
  • Versatile — transcription, translation, language detection, timestamps

Model Details

Property Value
Base model openai/whisper-large-v3
Parameters 1.5B
Languages 99+
Input 16 kHz audio
Tasks Transcription, translation, language ID, timestamps
License Apache 2.0

Use Cases

This model powers premium speech recognition in Edgework.ai — bringing fast, cheap, and private inference as close to the user as possible. Choose this when quality is paramount:

  • Professional transcription of therapy/coaching sessions
  • High-accuracy multilingual emotion journaling
  • Meeting transcription with speaker diarization
  • Subtitle generation for wellness content

Related Models

Model Parameters Languages Use case
whisper-small-onnx 244M 99 Lightweight multilingual
whisper-large-v3-onnx 1.5B 99+ Best multilingual quality
whisper-large-v3-turbo-onnx 809M 99+ Fast, high-quality
parakeet-ctc-0.6b-onnx 0.6B English Best English-only ASR

About

Published by AFFECTIVELY · Managed by @buley

We convert, quantize, and publish production-ready ONNX models for edge and in-browser inference. Every release is tested for correctness and stability before publication.

Downloads last month
23
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for affectively-ai/whisper-large-v3-onnx

Quantized
(23)
this model