Skip to content

happyme531

whisper-large-v3-turbo-RKNN2

happyme531/whisper-large-v3-turbo-RKNN2

whisper-large-v3-turbo-RKNN2 is a automatic speech recognition model from happyme531. Use it when you need speech turned into text. The card lists the license as agpl-3.0.

Whisper 是由 OpenAI 的 Alec Radford 等人提出的自动语音识别(ASR)和语音翻译前沿模型,相关论文为《通过大规模弱监督实现鲁棒语音识别》。该模型基于超过 500 万小时的标注数据训练,在零样本设定下展现出强大的跨数据集和跨领域泛化能力。 Whisper large-v3-turbo 是经过剪枝的 Whisper large-v3 微调版本。换言之,该模型与原始架构完全相同,仅将解码层数量从 32 层缩减…

Downloads · 30 days

17

14% of all-time downloads

All-time downloads

124

Public

Repo size

3.2 GB

Likes

1

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.rknn1.8 GB · 99%

At a glance

Task
Automatic Speech Recognition
License
agpl-3.0
Model type
whisper
Access
Public
Created
Mar 8, 2026
Updated
May 8, 2026
SHA
791cf8c7

Base models

Task
Automatic Speech Recognition
Type
whisper
License
agpl-3.0
Languages
en, zh, de, es, ru, ko
Created
Mar 8, 2026
Updated
May 8, 2026