OpenCodePapers

speech-recognition-on-mediaspeech

Speech Recognition
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeWER for ArabicWER for FrenchWER for SpanishWER for TurkishModelNameReleaseDate
MediaSpeech: Multilanguage ASR Benchmark and Dataset✓ Link0.13000.19150.18260.1422Quartznet2021-03-30
MediaSpeech: Multilanguage ASR Benchmark and Dataset✓ Link0.23330.17590.08790.0768Wit2021-03-30
MediaSpeech: Multilanguage ASR Benchmark and Dataset✓ Link0.30160.16830.12960.2296Azure2021-03-30
MediaSpeech: Multilanguage ASR Benchmark and Dataset✓ Link0.30850.21110.19700.3050VOSK2021-03-30
MediaSpeech: Multilanguage ASR Benchmark and Dataset✓ Link0.44640.23850.21760.2707Google2021-03-30
MediaSpeech: Multilanguage ASR Benchmark and Dataset✓ Link0.95960.31130.24690.5812wav2vec2021-03-30
MediaSpeech: Multilanguage ASR Benchmark and Dataset✓ Link0.47410.4236Deepspeech2021-03-30
MediaSpeech: Multilanguage ASR Benchmark and Dataset✓ Link0.3070Silero2021-03-30
Check out how to contribute new results.