HyperAI
StartseiteNeuigkeitenNeueste ForschungsarbeitenTutorialsDatensätzeWikiSOTALLM-ModelleGPU-RanglisteVeranstaltungen
Suche
Über
HyperAI

Automatic Lyrics Transcription On Jam Alt

Metriken

Case-Sensitive Word Error Rate
Line break F1
Punctuation F1
Word Error Rate (WER)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname
Case-Sensitive Word Error Rate
Line break F1
Punctuation F1
Word Error Rate (WER)
Paper TitleRepository
Whisper v3 +demucs51.665.733.048.0Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v2 +demucs49.861.241.644.5Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v339.773.543.035.5Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v2-69.341.735.7Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
OWSM v3.1 +demucs +lang72.641.120.066.5Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v2 +demucs-61.228.044.0Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
Whisper v3 +demucs +lang50.465.833.746.6Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v3-73.541.635.5Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
Whisper v3 +demucs-65.729.047.9Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
Whisper v242.169.344.237.8Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v3 +lang37.273.943.732.6Lyrics Transcription for Humans: A Readability-Aware Benchmark
AudioShake v3 20.1 84.457.016.1Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v2 +lang32.670.445.027.9Lyrics Transcription for Humans: A Readability-Aware Benchmark
AudioShake v1-82.350.526.0Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
OWSM v3.1 +lang75.037.822.569.3Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v2 +demucs +lang39.360.639.433.5Lyrics Transcription for Humans: A Readability-Aware Benchmark
0 of 16 row(s) selected.