Papers with Code · CC BY-SA 4.0

AudioCaps

아카이브 평가 23건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
ETTA-FT-AC-100k	FAD 2.03 FD 10.10 CLAP_MS 0.43 FD_openl3 61.79 CLAP_LAION 0.60 KL_passt 1.13 IS 14.29	ETTA: Elucidating the Design Space of Text-to-Audio Models 2024-12-26	코드 1
TangoFlux	FD_openl3 75.1 CLAP_LAION 0.488 KL_passt 1.15 IS 12.2	TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization 2024-12-30	코드 1
Stable Audio Open	CLAP_MS 0.34 FD_openl3 78.24 CLAP_LAION 0.35 KL_passt 2.14	Stable Audio Open 2024-07-19	코드 1
TangoFlux-base	FD_openl3 79.7 CLAP_LAION 0.438 KL_passt 1.23 IS 10.7	TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization 2024-12-30	코드 1
ETTA	FAD 2.51 FD 13.12 CLAP_MS 0.43 FD_openl3 80.13 CLAP_LAION 0.54 KL_passt 1.22 IS 14.36	ETTA: Elucidating the Design Space of Text-to-Audio Models 2024-12-26	코드 1
Stable Audio	FD_openl3 103.66 CLAP_LAION 0.41 KL_passt 2.89	Fast Timing-Conditioned Latent Audio Diffusion 2024-02-07	코드 1 · 코드 2
Stable Audio 2.0	FD_openl3 110.62 KL_passt 2.70	Long-form music generation with latent diffusion 2024-04-16	코드 1
AudioLDM2-large	FAD 2.02 FD 26.18 CLAP_MS 0.37 FD_openl3 158.04 CLAP_LAION 0.53 KL_passt 1.68 IS 8.55	AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining 2023-08-10	코드 1 · 코드 2
AudioGen	FAD 3.13 FD_openl3 185.53 KL_passt 1.42	AudioGen: Textually Guided Audio Generation 2022-09-30	코드 1
Audiobox Sound	FAD 0.77 FD 8.30 CLAP_LAION 0.71 IS 12.70	Audiobox: Unified Audio Generation with Natural Language Prompts 2023-12-25	연결 없음
GenAu-Large	FAD 1.21 FD 16.51 CLAP_MS 0.668	Taming Data and Transformers for Audio Generation 2024-06-27	코드 1
Re-AudioLDM-L	FAD 1.37	Retrieval-Augmented Text-to-Audio Generation 2023-09-14	연결 없음
AudioLDM 2-AC-Large	FAD 1.42 CLAP_LAION 0.243	AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining 2023-08-10	코드 1 · 코드 2
TANGO	FAD 1.59 FD 24.52	Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model 2023-04-24	코드 1
Auffusion	FAD 1.63 FD 21.99	Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation 2024-01-02	코드 1
Auffusion-Full	FAD 1.76 FD 23.08	Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation 2024-01-02	코드 1
Make-An-Audio 2	FAD 1.80 FD 11.75	Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation 2023-05-29	코드 1
CoDi	FAD 1.80 FD 22.90	Any-to-Any Generation via Composable Diffusion 2023-05-19	코드 1 · 코드 2
AudioLDM-L-Full	FAD 1.96 FD 23.31	AudioLDM: Text-to-Audio Generation with Latent Diffusion Models 2023-01-29	코드 1 · 코드 2 · 코드 3 · 코드 4
Consistency TTA (Single-step generation)	FAD 2.18 FD 20.44	ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation 2023-09-19	코드 1
Tango-AF&AC-FT-AC	FAD 2.54 FD 17.19 CLAP_LAION 0.527 IS 11.04	Improving Text-To-Audio Models with Synthetic Captions 2024-06-18	코드 1
Make-An-Audio	FAD 2.66 FD 18.32	Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models 2023-01-30	코드 1
Diffsound	FAD 7.75 FD 47.68	Diffsound: Discrete Diffusion Model for Text-to-sound Generation 2022-07-20	코드 1