Guanbo Wang 48a6a9a549
GigaSpeech RNN-T experiments (#318)
* Copy RNN-T recipe from librispeech

* flake8

* flake8

* Update params

* gigaspeech decode

* black

* Update results

* syntax highlight

* Update RESULTS.md

* typo
2022-05-13 11:03:26 +08:00
..
2022-05-07 08:10:54 +08:00
2022-04-14 16:07:22 +08:00
2022-04-14 16:07:22 +08:00
2022-04-14 16:07:22 +08:00
2022-05-13 11:03:26 +08:00
2022-05-13 11:03:26 +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
conformer_ctc 10.47 10.58
pruned_transducer_stateless2 10.52 10.62

See RESULTS for details.