MMAE

MMAE: A Massive Multitask Audio Editing Benchmark 📖 arXiv 🎬 MMAE Demo Video 🛠️ GitHub Code 🔊 HuggingFace Audio Download Overview of MMAE We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing. MMAE extends to a broad spectrum of real-world scenarios, encompassing 7 distinct audio modalities, including sound, speech, music, and… See the full description on the dataset page:

Source: Hugging Face Hub (BoJack/MMAE). Metadata imported from the dataset’s Hub tags.