Speech Recognition on Jam-ALT

Metric: Case-Sensitive Word Error Rate (lower is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Case-Sensitive Word Error Rate▲	Extra Data	Paper	Date↕	Code
1	AudioShake v3	20.1	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
2	Whisper v2 +lang	32.6	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
3	Whisper v3 +lang	37.2	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
4	Whisper v2 +demucs +lang	39.3	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
5	Whisper v3	39.7	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
6	Whisper v2	42.1	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
7	Whisper v2 +demucs	49.8	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
8	Whisper v3 +demucs +lang	50.4	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
9	Whisper v3 +demucs	51.6	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
10	OWSM v3.1 +demucs +lang	72.6	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
11	OWSM v3.1 +lang	75	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code

#1AudioShake v3SOTA
20.1
Case-Sensitive Word Error Rate· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#2Whisper v2 +langSOTA
32.6
Case-Sensitive Word Error Rate· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#3Whisper v3 +langSOTA
37.2
Case-Sensitive Word Error Rate· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#4Whisper v2 +demucs +langSOTA
39.3
Case-Sensitive Word Error Rate· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#5Whisper v3SOTA
39.7
Case-Sensitive Word Error Rate· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#6Whisper v2SOTA
42.1
Case-Sensitive Word Error Rate· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#7Whisper v2 +demucsSOTA
49.8
Case-Sensitive Word Error Rate· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#8Whisper v3 +demucs +langSOTA
50.4
Case-Sensitive Word Error Rate· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#9Whisper v3 +demucsSOTA
51.6
Case-Sensitive Word Error Rate· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#10OWSM v3.1 +demucs +langSOTA
72.6
Case-Sensitive Word Error Rate· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#11OWSM v3.1 +langSOTA
75
Case-Sensitive Word Error Rate· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code