Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Model basics

Reasoning traces

Not supported

Context length

2K tokens

Max output length

No data

Model type

基础大模型

Release date

2022-12-09

Model file size

6.17

MoE architecture

Total params / Active params

15.5B / N/A

Knowledge cutoff

No data

Inference modes

No mode data

Open source & experience

Code license

No data

Weights license

No data

GitHub repo

https://github.com/openai/whisper

Hugging Face

https://huggingface.co/openai/whisper-large-v2

Live demo

No live demo

Official resources

Paper

Robust Speech Recognition via Large-Scale Weak Supervision

DataLearnerAI blog

No blog post yet

API details

API speed

No data

No public API pricing yet.

Benchmark Scores

No benchmark data to show.

Publisher

OpenAI

View publisher details

Model Overview

Whisper V2是OpenAIWhisper的第二个版本，它的参数与第一个版本中最大的模型一致，15.5亿。它是第一个模型继续训练了2.5倍的结果，且新增了SpecAugment、Stochastic depth和BPE Dropout等正则化技术。除此之外，模型架构和参数大小均与第一个版本相同。

Whisper第一个版本的模型如下：

第二个版本就是large的v2版本。‘

Whisper V2版本的官方发布说明： https://github.com/openai/whisper/discussions/661

Foundation model

Whisper

View details

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送