2023-10-17 21:42:41 -05:00
..
2023-10-17 20:07:32 +08:00
2022-11-22 11:39:21 +08:00
2023-10-17 19:40:19 +08:00
2023-10-17 20:02:53 +08:00
2022-04-14 16:07:22 +08:00

GigaSpeech

GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio, collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. More details can be found: https://github.com/SpeechColab/GigaSpeech

Download

Apply for the download credentials and download the dataset by following https://github.com/SpeechColab/GigaSpeech#download. Then create a symlink

ln -sfv /path/to/GigaSpeech download/GigaSpeech

Performance Record

Dev Test
zipformer 10.25 10.38
conformer_ctc 10.47 10.58
pruned_transducer_stateless2 10.40 10.51

See RESULTS for details.