Audio-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen3_omni_moe
text-to-audio
audio
audio-language-model
instruction-following
rubric-based-evaluation
judge-model
Instructions to use cucl2/AnyAudio-Judge-30B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cucl2/AnyAudio-Judge-30B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("cucl2/AnyAudio-Judge-30B") model = AutoModelForTextToWaveform.from_pretrained("cucl2/AnyAudio-Judge-30B") - Notebooks
- Google Colab
- Kaggle
Switch citation to @misc preprint
Browse files
README.md
CHANGED
|
@@ -63,9 +63,10 @@ Apache-2.0, inheriting the license of the base Qwen3-Omni-30B-A3B-Captioner mode
|
|
| 63 |
## Citation
|
| 64 |
|
| 65 |
```bibtex
|
| 66 |
-
@
|
| 67 |
-
title
|
| 68 |
-
|
| 69 |
-
year
|
|
|
|
| 70 |
}
|
| 71 |
```
|
|
|
|
| 63 |
## Citation
|
| 64 |
|
| 65 |
```bibtex
|
| 66 |
+
@misc{anyaudiojudge2026,
|
| 67 |
+
title = {AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following},
|
| 68 |
+
author = {Anonymous Authors},
|
| 69 |
+
year = {2026},
|
| 70 |
+
note = {Preprint, under submission}
|
| 71 |
}
|
| 72 |
```
|