|
Download README.md from Missouter/AcoustiTrace-RT60: direct link, hf CLI and curl.
- Browser
- Download file 2.36 kB
-
https://huggingface.co/Missouter/AcoustiTrace-RT60/resolve/main/README.md
- Command line
-
hf download hf://Missouter/AcoustiTrace-RT60/README.md
-
curl -L -o README.md https://huggingface.co/Missouter/AcoustiTrace-RT60/resolve/main/README.md
2.36 kB
| base_model: Qwen/Qwen3-VL-8B-Instruct | |
| license: other | |
| license_name: acoustitrace-rt60-research-license | |
| license_link: https://huggingface.co/Missouter/AcoustiTrace-RT60/blob/main/LICENSE | |
| tags: | |
| - acoustitrace | |
| - audio-visual | |
| - room-acoustics | |
| - rt60 | |
| - lora | |
| # AcoustiTrace RT60 Evaluator | |
| This repository contains the learned visual RT60 component used by | |
| [AcoustiTrace](https://leader-sheng.github.io/AcoustiTrace/), an audio-visual | |
| benchmark for diagnosing acoustic plausibility in generated videos. | |
| The checkpoint estimates scene-consistent reverberation time at 500 Hz from | |
| visual acoustic cues. It contains a LoRA adapter for | |
| [`Qwen/Qwen3-VL-8B-Instruct`](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) | |
| and a Sabine-guided continuous physics head. It does **not** include a copy of | |
| the Qwen3-VL base model. | |
| ## Files | |
| ```text | |
| physics_head.pt | |
| vlm_adapter/ | |
| adapter_config.json | |
| adapter_model.safetensors | |
| processor/ | |
| acoustitrace_rt60_config.json | |
| SHA256SUMS | |
| ``` | |
| ## Use with AcoustiTrace | |
| ```bash | |
| git clone https://github.com/Leader-sheng/AcoustiTrace.git | |
| cd AcoustiTrace | |
| python scripts/download_weights.py \ | |
| --repo-id Missouter/AcoustiTrace-RT60 \ | |
| --local-dir checkpoints/acoustitrace-rt60 | |
| python scripts/verify_checkpoint.py checkpoints/acoustitrace-rt60 | |
| ``` | |
| The frozen base model is downloaded separately from | |
| `Qwen/Qwen3-VL-8B-Instruct`. Full evaluator setup and end-to-end commands are | |
| provided in the AcoustiTrace repository. | |
| ## Training sources and license | |
| The RT60 supervision combines Matterport3D RGB-D observations, SoundSpaces 2.0 | |
| room-acoustic simulation, and absorption coefficients from the PTB Room | |
| Acoustics Absorption Coefficient Database. No upstream training data is | |
| included in this repository. | |
| The model artifacts are available for non-commercial academic and research | |
| use under the terms in [LICENSE](LICENSE). In particular, use remains subject | |
| to the Matterport3D Academic Use Terms. The Qwen3-VL base model is separately | |
| licensed under Apache-2.0. | |
| ## Links | |
| - [Paper](https://arxiv.org/abs/2608.02035) | |
| - [Project page](https://leader-sheng.github.io/AcoustiTrace/) | |
| - [Code](https://github.com/Leader-sheng/AcoustiTrace) | |
| ## Scope | |
| This model is released as the visual RT60 evaluator for AcoustiTrace. Its | |
| outputs are diagnostic estimates for benchmark evaluation rather than direct | |
| room-acoustic measurements. | |