HyperAI超神经

首页算力平台文档资讯论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Automatic Lyrics Transcription On Jam Alt

评估指标

Case-Sensitive Word Error Rate

Line break F1

Punctuation F1

Word Error Rate (WER)

评测结果

各个模型在此基准测试上的表现结果

					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.