TextsAudio

Audio-alpaca

Introduced in Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization2024

About this Dataset

Audio-alpaca: A preference dataset for aligning text-to-audio models

Audio-alpaca is a pairwise preference dataset containing about 15k (prompt,chosen, rejected) triplets where given a textual prompt, chosen is the preferred generated audio and rejected is the undesirable audio.

Field details

prompt: Given textual prompt

chosen: The preferred audio sample

rejected: The rejected audio sample

Source: Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization

Dataset Variants

Audio-alpaca

Papers1

Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization

This work fine-tune the publicly available Tango text-to-audio model using diffusion-DPO (direct preference optimization) loss on the authors' preference dataset and shows that it leads to improved audio output over Tango and AudioLDM2, in terms of both automatic- and manual-evaluation metrics.

Tasks

EDIT

Audio Generation

Similar Datasets

GLUE

MultiNLI

Penn Treebank

Statistics

Papers

1

Tasks

62

Introduced

2024

Modalities

TextsAudio

Languages

English