How to use mobilint/Qwen3-ASR-1.7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mobilint/Qwen3-ASR-1.7B", trust_remote_code=True)
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mobilint/Qwen3-ASR-1.7B", trust_remote_code=True, device_map="auto")
How to use mobilint/Qwen3-ASR-1.7B with Mobilint:
# pip install mblt-model-zoo from mblt_model_zoo.vision import MBLT_Engine model = MBLT_Engine( model_cls="Qwen3-ASR-1.7B", model_type="DEFAULT", model_path="", core_mode="global8", ) try: image = model.preprocess("path/to/image.jpg") output = model(image) result = model.postprocess(output) finally: model.dispose()
