OpenVoiceOS/qwen3-asr-0.6b-onnx

Qwen3-ASR-0.6B — ONNX (speech-llm)

ONNX export of Qwen/Qwen3-ASR-0.6B-hf for onnx-asr with the speech-llm model type (requires the speech-llm model-family patches, see TigreGotico/onnx-asr PR #3).

Three-graph layout: encoder.onnx (audio -> projected audio embeddings), embed_tokens.onnx, and a merged prefill+decode decoder.onnx with a 28-layer KV cache. Prompt token ids are baked into config.json, so no tokenizer is needed at runtime. fp32 output matches native transformers character-for-character on FLEURS test clips (en, pt). fp32 and int8 graphs included.

Usage

import onnx_asr
model = onnx_asr.load_model("speech-llm", "path/to/this/repo")  # or quantization="int8"
print(model.recognize("audio_16khz.wav"))

License: Apache-2.0 (inherited from the source model).