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
Git repo URL: git@github.com:poleval/2024-asr-bigos.git / Branch: main
Run git clone --single-branch git@github.com:poleval/2024-asr-bigos.git -b main to get the challenge data
Browse at https://github.com/poleval/2024-asr-bigos/tree/main
Leaderboard
| # | submitter | when | ver. | description | test-A CER | test-A WER | test-B CER | test-B WER | × | |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | [name not given] | 2024-05-24 10:10 | 1.0.8 poleval-2024 | test test | 0.0 | 0.0 | 0.0 | 0.0 | 4 | |
| 2 | Samsung R&D Poland | 2024-08-28 10:57 | 1.0.14 poleval-2024 | whisper-large-v3-mix-01-25k-beam4 poleval-2024 | 6.904756726189182e-2 | 0.1127222835005784 | 6.848707045779368e-2 | 0.11073225726620288 | 8 | |
| 3 | UAM | 2024-03-11 08:37 | 1.0.8 poleval-2024 | Test dev-0 test | 0.967452774624381 | 0.9999846801991574 | 0.9671964713226366 | 0.9999719062542921 | 1 | |
| 4 | Metamedia Technologies | 2024-10-01 07:13 | 1.0.14 poleval-2024 | 00 test submission asr mt5 poleval-2024 test | 0.9397742349435587 | 1.0180248042829088 | 0.9472076982485419 | 1.0206505898204417 | 1 |