HyperAI超神经

Automatic Lyrics Transcription On Jam Alt 2

评估指标

Case Error Rate
Line break F-1
Punctuation F-1
Word Error Rate (WER)

评测结果

各个模型在此基准测试上的表现结果

模型名称
Case Error Rate
Line break F-1
Punctuation F-1
Word Error Rate (WER)
Paper TitleRepository
Whisper v3 +demucs3.652.428.761.5Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
OWSM v3.1 +demucs +lang-33.59.070.8Lyrics Transcription for Humans: A Readability-Aware Benchmark
AudioShake v3-81.5 56.712.6Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v2 +demucs +lang-52.634.334.9Lyrics Transcription for Humans: A Readability-Aware Benchmark
AudioShake v14.182.747.822.5Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
Whisper v2 +lang-71.552.521.9Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v3 +lang-74.544.522.4Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v3 +demucs-52.332.461.5Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v2 +demucs7.156.417.238.8Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
Whisper v3-73.742.528.6Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v26.571.750.025.7Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
Whisper v2 +demucs-56.640.439.6Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v2-71.752.825.8Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v3 5.073.741.928.6Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
OWSM v3.1 +lang-30.28.873.3Lyrics Transcription for Humans: A Readability-Aware Benchmark
Whisper v3 +demucs +lang-54.734.458.6Lyrics Transcription for Humans: A Readability-Aware Benchmark
0 of 16 row(s) selected.