Speech Recognition on Jam-ALT German

Metric: Punctuation F-1 (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Punctuation F-1▼	Extra Data	Paper	Date↕	Code
1	AudioShake v3	57.1	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
2	Whisper v2 +demucs +lang	49.2	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
3	Whisper v2 +demucs	49.1	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
4	AudioShake v1	48.5	No	Jam-ALT: A Formatting-Aware Lyrics Transcription...	2023-11-23	Code
5	Whisper v2 +lang	48.4	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
6	Whisper v3 +lang	47.4	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
7	Whisper v3	47.3	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
8	Whisper v2	47.1	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
9	Whisper v3 +demucs +lang	46.9	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
10	Whisper v3 +demucs	45.4	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
11	Whisper v3	41.2	No	Jam-ALT: A Formatting-Aware Lyrics Transcription...	2023-11-23	Code
12	Whisper v2	38.7	No	Jam-ALT: A Formatting-Aware Lyrics Transcription...	2023-11-23	Code
13	Whisper v3 +demucs	34	No	Jam-ALT: A Formatting-Aware Lyrics Transcription...	2023-11-23	Code
14	Whisper v2 +demucs	30.2	No	Jam-ALT: A Formatting-Aware Lyrics Transcription...	2023-11-23	Code
15	OWSM v3.1 +lang	28.6	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code
16	OWSM v3.1 +demucs +lang	24.7	No	Lyrics Transcription for Humans: A Readability-A...	2024-07-30	Code

#1AudioShake v3SOTA
57.1
Punctuation F-1· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#2Whisper v2 +demucs +lang
49.2
Punctuation F-1· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#3Whisper v2 +demucs
49.1
Punctuation F-1· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#4AudioShake v1SOTA
48.5
Punctuation F-1· 2023-11-23
Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark Code
#5Whisper v2 +lang
48.4
Punctuation F-1· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#6Whisper v3 +lang
47.4
Punctuation F-1· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#7Whisper v3
47.3
Punctuation F-1· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#8Whisper v2
47.1
Punctuation F-1· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#9Whisper v3 +demucs +lang
46.9
Punctuation F-1· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#10Whisper v3 +demucs
45.4
Punctuation F-1· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#11Whisper v3
41.2
Punctuation F-1· 2023-11-23
Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark Code
#12Whisper v2
38.7
Punctuation F-1· 2023-11-23
Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark Code
#13Whisper v3 +demucs
34
Punctuation F-1· 2023-11-23
Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark Code
#14Whisper v2 +demucs
30.2
Punctuation F-1· 2023-11-23
Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark Code
#15OWSM v3.1 +lang
28.6
Punctuation F-1· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code
#16OWSM v3.1 +demucs +lang
24.7
Punctuation F-1· 2024-07-30
Lyrics Transcription for Humans: A Readability-Aware Benchmark Code