Skip to content

infodeliverailab

qwen3-omni-jp-vllm

infodeliverailab/qwen3-omni-jp-vllm

qwen3-omni-jp-vllm is a automatic speech recognition model from infodeliverailab. Use it when you need speech turned into text. It is set up for vllm.

Qwen3-Omni-30B-A3B-Instruct をそのままの重みで日本語音声書き起こしに使う「レシピ」。 モデル重みは Qwen 公式そのまま (Qwen/Qwen3-Omni-30B-A3B-Instruct) を使い、 本レポは セットアップ + サーバ実装 だけを配布します。

Downloads · 30 days

0

Access

Public

Updated Jul 15, 2026

Repo size

—

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.py11 KB · 46%

At a glance

Task
Automatic Speech Recognition
Library
vllm
Access
Public
Created
Jul 15, 2026
Updated
Jul 15, 2026
SHA
b109fcf0

Base models

Task
Automatic Speech Recognition
Library
vllm
Languages
ja
Created
Jul 15, 2026
Updated
Jul 15, 2026