Animescore

--- language: - ja license: mit tags: - audio - speech - preference - anime library_name: transformers pipeline_tag: audio-classification --- # AnimeScore Try the interactive demo: [AnimeScore Demo Space](https://huggingface.co/spaces/spellbrush/animescore-demo). A learned scorer for anime-like speech style. Given an audio clip, it returns a scalar score; higher is more anime-like. This is the official Huggingface model repository for the paper "[AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style](https://arxiv.org/abs/2603.11482)". For more details, please visit our [GitHub Repository](https://github.com/sizigi/animescore). ## Checkpoint We release the HuBERT-based model, which achieved the best performance among the backbones we evaluated (pairwise accuracy 82.4%, AUC 0.908). | File | Size | Notes | |---|---:|---| | `model.safetensors` | ~9 MB | Released head weights | | `config.json` | — | Model config | | `modeling_animescore.py` | — | Custom modeling code (loaded via `trust_remote_code=True`) | ## How to use ```bash pip install -r requirements.txt ``` ```python import torch, torchaudio from transformers import AutoModel device = "cuda" if torch.cuda.is_available() else "cpu" model = AutoModel.from_pretrained( "spellbrush/animescore", trust_remote_code=True, ).eval().to(device) wav, sr = torchaudio.load("sample.wav") if wav.size(0) > 1: wav = wav.mean(0, keepdim=True) # mono if sr != 16000: wav = torchaudio.functional.resample(wav, sr, 16000) with torch.no_grad(): s = model.score(wav.to(device)).item() print(f"AnimeScore: {s:.3f}") ``` Pairwise probability: ```python sa = model.score(wav_a.to(device)) sb = model.score(wav_b.to(device)) p_a_gt_b = torch.sigmoid(sa - sb).item() ``` CLI: `python example_inference.py --ckpt . --wav sample.wav` or deploy this directory as a HuggingFace Space (SDK = `gradio`). ## Citation ```bibtex @inproceedings{park2026animescore, title = {AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style}, author = {Park, Joonyong and Li, Jerry}, booktitle = {Interspeech}, year = {2026} } ``` ## License MIT License.

Source context: 408 downloads · 7 likes · Pipeline audio-classification · Library transformers · Repo spellbrush/animescore

Source context: 27 downloads · 7 likes · Pipeline audio-classification · Library transformers · Repo spellbrush/animescore