Rikunarita-ORG
/

Qwen3-ASR-1.7B-Audio-Encoder-Extracted

Automatic Speech Recognition

Model card Files Files and versions

Qwen3-ASR-1.7B Audio Encoder (Extracted)

This repository contains only the audio encoder part extracted from Qwen/Qwen3-ASR-1.7B.

Model Details

Original Model: Qwen/Qwen3-ASR-1.7B
Extracted Prefix: thinker.audio_tower.
Format: Safetensors (model.safetensors)
Use Case: Multimodal AI development (Switching to your own multimodal AI, etc.), speech embedding, audio feature extraction.

Downloads last month: -; Downloads are not tracked for this model. How to track

Safetensors

Model size

0.3B params

Tensor type

BF16

·

Model tree for Rikunarita-ORG/Qwen3-ASR-1.7B-Audio-Encoder-Extracted

Base model

Qwen/Qwen3-ASR-1.7B

Finetuned

(59)

this model