espnet/espnet

Audio encoder development plan

Open

#6,021 创建于 2025年1月21日

在 GitHub 查看
 (0 评论) (0 反应) (0 负责人)Python (2,025 fork)batch import
Help wantedNew FeaturesRoadmapSED

仓库指标

Star
 (7,400 star)
PR 合并指标
 (平均合并 22天 14小时) (30 天内合并 22 个 PR)

描述

Evaluation Recipes

  • Machine sounds anomaly detection @shimhz [to be done on top of espnet/espnet/pull/5998]
  • Sound event detection @Shikhar-S from BEAN [26th Jan]
    • DCASE dataset @Shikhar-S [26th Jan]
      • Rfcx @popcornell
      • Gibbons @popcornell
      • Hiceas @popcornell
      • Enabirds @popcornell
  • Audio Captioning
  • Audio Entailment @Shikhar-S [30th Jan]
    • Audio Question Answering
  • FSD-50K Multi-label classification @juice500ml
  • Music @fukafilet
    • Instrument classification
    • Genre classisifcation

BEATs pre-training

  • Code for training @Shikhar-S [24th Jan]
    • AudioSet @Shikhar-S
    • AudioSet + inat @Shikhar-S

Pull Requests

Timeline

  • 24th Jan: Provide pre-training code to @juice500ml
  • 26th Jan: Provide sed task recipe to @popcornell

Any suggestions are welcome.

贡献者指南