Polish Automatic Speech Recognition Challenge

Automatic speech recognition (ASR) has made significant progress over the last decade. Improvements in deep learning and increased data availability have resulted in accuracy levels for artificial speech transcription that are on par with human transcription, at least in specific domains, tasks, and speech characteristics. ASR technology has expanded to cover many new languages, use cases, user demographics, and devices. However, achieving robust speech recognition remains a challenge for many low-resource languages, specific speaker groups, application domains, and acoustic conditions. [ver. 1.0.14]

Deadline: 2024-10-28 23:59:00 UTC

poleval-2024 asr

Log in to write a comment

Paweł Cyrta   2024-10-01 07:13

submitted a solution:00 test submission

LIT-MR   2024-09-04 13:37

submitted a solution:whisper-large-v3-mix-01-50k

LIT-MR   2024-09-04 13:35

submitted a solution:whisper-large-v3-mix-00-18k-beam4

LIT-MR   2024-09-04 13:33

submitted a solution:whisper-large-v3-baseline-13k-beam4

LIT-MR   2024-08-28 10:57

submitted a solution:whisper-large-v3-mix-01-25k-beam4

LIT-MR   2024-08-28 08:49

submitted a solution:conformer-baseline-500k

LIT-MR   2024-08-28 08:19

submitted a solution:conformer-mix-00-500k

LIT-MR   2024-08-28 06:53

submitted a solution:conformer-mix-01-500k

LIT-MR   2024-08-27 11:57

submitted a solution:whisper-large-v3-mix-01-25k

[name not given]   2024-05-24 10:10

submitted a solution:test

[name not given]   2024-05-24 10:08

submitted a solution:test error

[name not given]   2024-05-24 09:37

submitted a solution:test

ryssta   2024-03-11 08:37

submitted a solution:Test dev-0

[name not given]   2024-03-10 14:13

submitted a solution:1234