Skip to content

JazerJu

qwen3-asr-ctc-aiinfra

JazerJu/qwen3-asr-ctc-aiinfra

qwen3-asr-ctc-aiinfra is a automatic speech recognition model from JazerJu. Use it when you need speech turned into text. It is set up for pytorch. The card lists the license as apache-2.0.

新增 a7avg5/(2026-11):修 aiinfra4 在纯英文音频上串出中文的问题, 85.45M 参数、self-conditioned,step 412000–420000 五点平均。根目录仍是 aiinfra4 (step 339707),未覆盖。回归结果与口径见 bench-asr-ctc, ONNX 头见 qwen-ctc-a7avg5。

Downloads · 30 days

56

58% of all-time downloads

All-time downloads

96

Public

Repo size

684 MB

Likes

1

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors684 MB · 100%

At a glance

Task
Automatic Speech Recognition
Library
pytorch
License
apache-2.0
Model type
ctc-head
Access
Public
Created
Sep 19, 2026
Updated
Nov 6, 2026
SHA
150528f4

Base models

Task
Automatic Speech Recognition
Library
pytorch
Type
ctc-head
License
apache-2.0
Languages
zh, en, yue, ja, ko, de
Created
Sep 19, 2026
Updated
Nov 6, 2026