Audio Classification
Transformers
Safetensors
qwen3_omni_moe
text-to-audio
audio
turn-taking
end-of-turn-detection
interruption-detection
lora
ms-swift
custom-inference
Instructions to use Beagledata/Turn-Detection-Jev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Beagledata/Turn-Detection-Jev with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="Beagledata/Turn-Detection-Jev")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Beagledata/Turn-Detection-Jev") model = AutoModelForMultimodalLM.from_pretrained("Beagledata/Turn-Detection-Jev", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download scoring_head.json from Beagledata/Turn-Detection-Jev: direct link, hf CLI and curl.
- Browser
- Download file 688 Bytes
-
https://huggingface.co/Beagledata/Turn-Detection-Jev/resolve/main/scoring_head.json
- Command line
-
hf download hf://Beagledata/Turn-Detection-Jev/scoring_head.json
-
curl -L -o scoring_head.json https://huggingface.co/Beagledata/Turn-Detection-Jev/resolve/main/scoring_head.json
688 Bytes
| { | |
| "checkpoint_kind": "merged", | |
| "base_model_name_or_path": "/workspace/ckpts/Qwen3-Omni-30B-A3B-Instruct", | |
| "base_model_revision": null, | |
| "model_type": "audio_jev", | |
| "prompt_version": "audio-jev-labels-v4", | |
| "slot_ids": [ | |
| 32, | |
| 33, | |
| 34, | |
| 35, | |
| 36, | |
| 37, | |
| 38, | |
| 39, | |
| 40, | |
| 41, | |
| 42, | |
| 43, | |
| 44, | |
| 45, | |
| 46, | |
| 47, | |
| 48, | |
| 49, | |
| 50, | |
| 51, | |
| 52, | |
| 53, | |
| 54, | |
| 55, | |
| 56, | |
| 57 | |
| ], | |
| "labels": [ | |
| "listen_complete", | |
| "listen_incomplete", | |
| "listen_background", | |
| "speak_interrupt", | |
| "speak_backchannel", | |
| "speak_incomplete", | |
| "speak_background" | |
| ], | |
| "head_type": "lm_head", | |
| "readout": "last_valid_token" | |
| } | |