Audio-Text-to-Text
Transformers
Safetensors
qwen2_5_omni
text-to-audio
audio
audio-question-answering
audio-classification
candidate-scoring
Instructions to use shlv/AudioJev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shlv/AudioJev with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("shlv/AudioJev") model = AutoModelForMultimodalLM.from_pretrained("shlv/AudioJev", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
17 days ago
-
Add links to paper and code
Verified signatureThis PR adds links to the paper and the code repository to the model card.1c3d89b
21 days ago
-
Keep only standard model assets and documentation
Verified signatureFollow the Qwen2.5-Omni-3B model repository layout: remove auxiliary training, evaluation, and release manifests. Retain checkpoint assets, model card, license, and the required derivative notice.d506a7b -
Keep model assets separate from AudioJev-Inference
Verified signatureRemove the bundled inference script and runtime requirements. Point the model card to the standalone AudioJev-Inference project and update the release manifest and notice. Model tensors are unchanged.4e0323d -
Release AudioJev RD-SKL lambda=0.5 seed=20261001
Verified signatureFixed final general-stage checkpoint after 4096 training updates. Original FP32 weight shards, tokenizer/processor, model card, Qwen Research License, and tested candidate-probability example.25bc587 -
initial commit
Verified signature1d6f4ed