← Automatic Lyrics Transcription

Papers with Code · CC BY-SA 4.0

Jam-ALT German

아카이브 평가 16건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

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
AudioShake v3	Word Error Rate (WER) 12.6 Punctuation F-1 57.1 Parenthesis F-1 76.6 Line break F-1 83.7 Section break F-1 74.5 Case-Sensitive Word Error Rate 17.5	Lyrics Transcription for Humans: A Readability-Aware Benchmark 2024-07-30	코드 1
Whisper v2 +lang	Word Error Rate (WER) 19.9 Punctuation F-1 48.4 Line break F-1 71.7 Case-Sensitive Word Error Rate 26.0	Lyrics Transcription for Humans: A Readability-Aware Benchmark 2024-07-30	코드 1
Whisper v2 +demucs +lang	Word Error Rate (WER) 23.9 Punctuation F-1 49.2 Line break F-1 70.6 Case-Sensitive Word Error Rate 30.4	Lyrics Transcription for Humans: A Readability-Aware Benchmark 2024-07-30	코드 1
AudioShake v1	Word Error Rate (WER) 24.4 Case Error Rate 4.1 Punctuation F-1 48.5 Parenthesis F-1 8.1 Line break F-1 81.2 Section break F-1 69.2	Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark 2023-11-23	코드 1
Whisper v3 +lang	Word Error Rate (WER) 35.9 Punctuation F-1 47.4 Line break F-1 71.1 Case-Sensitive Word Error Rate 40.4	Lyrics Transcription for Humans: A Readability-Aware Benchmark 2024-07-30	코드 1
Whisper v3	Word Error Rate (WER) 40.7 Punctuation F-1 47.3 Line break F-1 71.1 Section break F-1 1.2 Case-Sensitive Word Error Rate 44.6	Lyrics Transcription for Humans: A Readability-Aware Benchmark 2024-07-30	코드 1
Whisper v3	Word Error Rate (WER) 40.7 Case Error Rate 4.0 Punctuation F-1 41.2 Line break F-1 71.2 Section break F-1 1.2	Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark 2023-11-23	코드 1
Whisper v3 +demucs +lang	Word Error Rate (WER) 40.8 Punctuation F-1 46.9 Line break F-1 70.5 Case-Sensitive Word Error Rate 44.9	Lyrics Transcription for Humans: A Readability-Aware Benchmark 2024-07-30	코드 1
Whisper v3 +demucs	Word Error Rate (WER) 43.5 Punctuation F-1 45.4 Line break F-1 71.9 Case-Sensitive Word Error Rate 47.4	Lyrics Transcription for Humans: A Readability-Aware Benchmark 2024-07-30	코드 1
Whisper v3 +demucs	Word Error Rate (WER) 43.5 Case Error Rate 4.4 Punctuation F-1 34.0 Line break F-1 72.0	Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark 2023-11-23	코드 1
Whisper v2	Word Error Rate (WER) 45.4 Case Error Rate 5.3 Punctuation F-1 38.7 Line break F-1 69.9	Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark 2023-11-23	코드 1
OWSM v3.1 +demucs +lang	Word Error Rate (WER) 51.8 Punctuation F-1 24.7 Line break F-1 41.4 Case-Sensitive Word Error Rate 62.0	Lyrics Transcription for Humans: A Readability-Aware Benchmark 2024-07-30	코드 1
Whisper v2	Word Error Rate (WER) 54.5 Punctuation F-1 47.1 Line break F-1 70.0 Case-Sensitive Word Error Rate 59.3	Lyrics Transcription for Humans: A Readability-Aware Benchmark 2024-07-30	코드 1
OWSM v3.1 +lang	Word Error Rate (WER) 63.3 Punctuation F-1 28.6 Parenthesis F-1 0.0 Line break F-1 40.7 Case-Sensitive Word Error Rate 71.8	Lyrics Transcription for Humans: A Readability-Aware Benchmark 2024-07-30	코드 1
Whisper v2 +demucs	Word Error Rate (WER) 65.2 Punctuation F-1 49.1 Line break F-1 67.3 Case-Sensitive Word Error Rate 70.4	Lyrics Transcription for Humans: A Readability-Aware Benchmark 2024-07-30	코드 1
Whisper v2 +demucs	Word Error Rate (WER) 65.2 Case Error Rate 5.9 Punctuation F-1 30.2 Line break F-1 67.5	Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark 2023-11-23	코드 1