Modelpublic

adventists-ai/Qwen3-ASR-0.6B-Encoder

sourceHugging Faceapache-2.0updated 20h agoView on Hugging Face

0likes

Model Card

Qwen3-ASR-0.6B-Encoder

The audio encoder of Qwen/Qwen3-ASR-0.6B, extracted as a standalone transformers model (trust_remote_code=True), 18 layers, d_model 896. Weights are unchanged from Qwen3-ASR-0.6B.

The plain encoder, used by the last-layer (B) connectors.

Used by: DuplexJev-B-* (last-layer connectors). You normally do not load it yourself: Decider.from_pretrained("adventists-ai/DuplexJev-...") fetches it.

License: Apache-2.0, as the original Qwen3-ASR-0.6B. See https://github.com/adventists-ai/duplexjev.