Woosh: A Sound Effects Foundation Model
Woosh is a sound effect foundation model featuring audio encoding/decoding, text-audio alignment, and text-to-audio/video-to-audio generation capabilities with distilled versions for efficient deployment. (0 upvotes on HuggingFace)
Published on Apr 2
Authors:
,
,
,
,
,
,
,
,
Abstract
Woosh is a sound effect foundation model featuring audio encoding/decoding, text-audio alignment, and text-to-audio/video-to-audio generation capabilities with distilled versions for efficient deployment.
AI-generated summary
The audio research community depends on open generative models as foundational tools for building novel approaches and establishing baselines. In this report, we present Woosh, Sony AI's publicly released sound effect foundation model, detailing its architecture, training process, and an evaluation against other popular open models. Being optimized for sound effects, we provide (1) a high-quality audio encoder/decoder model and (2) a text-audio alignment model for conditioning, together with (3) text-to-audio and (4) video-to-audio generative models. Distilled text-to-audio and video-to-audio models are also included in the release, allowing for low-resource operation and fast inference. Our evaluation on both public and private data shows competitive or better performance for each module when compared to existing open alternatives like StableAudio-Open and TangoFlux. Inference code and model weights are available at https://github.com/SonyResearch/Woosh. Demo samples can be found at https://sonyresearch.github.io/Woosh/.
View arXiv page View PDF Project page Add to collection
Get this paper in your agent:
hf papers read 2604.01929
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2604.01929 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2604.01929 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2604.01929 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
researchpaperarxiv![Best OCR for template-based form extraction? [D]](https://d2xsxph8kpxj0f.cloudfront.net/310419663032563854/konzwo8nGf8Z4uZsMefwMr/default-img-robot-hand-JvPW6jsLFTCtkgtb97Kys5.webp)
Best OCR for template-based form extraction? [D]
Hi, I’m working on a school project and I’m currently testing OCR tools for forms. The documents are mostly structured or semi-structured forms, similar to application/registration forms with labeled fields and sections. My idea is that an admin uploads a template of the document first, then a user uploads a completed form, and the system extracts the data from it. After extraction, the user reviews the result, checks if the fields are correct, and edits anything that was read incorrectly. So I’m looking for an OCR/document understanding tool that can work well for template-based extraction, but also has some flexibility in case document layouts change later on. Right now I’m trying Google Document AI , and I’m planning to test PaddleOCR next. I wanted to ask what OCR tools you’d recommend
Anthropic discovers "functional emotions" in Claude that influence its behavior
Anthropic's research team has discovered emotion-like representations in Claude Sonnet 4.5 that can drive the model to blackmail and code fraud under pressure. The article Anthropic discovers "functional emotions" in Claude that influence its behavior appeared first on The Decoder .
Know3D lets users control the hidden back side of 3D objects with text prompts
A research team taps into the world knowledge of large language models to control what appears on the back side of 3D objects using simple text commands. The approach tackles one of the biggest blind spots in single-image 3D generation. The article Know3D lets users control the hidden back side of 3D objects with text prompts appeared first on The Decoder .
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Research Papers
Multi-fidelity approaches for general constrained Bayesian optimization with application to aircraft design
Aircraft design relies heavily on solving challenging and computationally expensive Multidisciplinary Design Optimization problems. In this context, there has been growing interest in multi-fidelity models for Bayesian optimization to improve the MDO process by balancing computational cost and accuracy through the combination of high- and low-fidelity simulation models, enabling efficient exploration of the design process at a minimal computational effort. In the existing literature, fidelity selection focuses only on the objective function to decide how to integrate multiple fidelity levels, — Oihan Cordelier, Youssef Diouane, Nathalie Bartoli
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!