Accueil Plateforme Docs Actualités Articles de recherche Tutoriels Ensembles de données Wiki SOTA Modèles LLM Classement GPU Événements

Français

Automatic Lyrics Transcription On Jam Alt

Métriques

Case-Sensitive Word Error Rate

Line break F1

Punctuation F1

Word Error Rate (WER)

Résultats

Résultats de performance de divers modèles sur ce benchmark

					Paper Title	Repository
AudioShake v3	20.1	84.4	57.0	16.1	Lyrics Transcription for Humans: A Readability-Aware Benchmark
AudioShake v1	-	82.3	50.5	26.0	Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
Whisper v3 +lang	37.2	73.9	43.7	32.6	Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v3	39.7	73.5	43.0	35.5	Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v3	-	73.5	41.6	35.5	Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
Whisper v2 +lang	32.6	70.4	45.0	27.9	Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v2	-	69.3	41.7	35.7	Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
Whisper v2	42.1	69.3	44.2	37.8	Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v3 +demucs +lang	50.4	65.8	33.7	46.6	Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v3 +demucs	51.6	65.7	33.0	48.0	Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v3 +demucs	-	65.7	29.0	47.9	Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
Whisper v2 +demucs	49.8	61.2	41.6	44.5	Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v2 +demucs	-	61.2	28.0	44.0	Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
Whisper v2 +demucs +lang	39.3	60.6	39.4	33.5	Lyrics Transcription for Humans: A Readability-Aware Benchmark
OWSM v3.1 +demucs +lang	72.6	41.1	20.0	66.5	Lyrics Transcription for Humans: A Readability-Aware Benchmark
OWSM v3.1 +lang	75.0	37.8	22.5	69.3	Lyrics Transcription for Humans: A Readability-Aware Benchmark

0 of 16 row(s) selected.