Speech recognition workshop
Sunday the 20th December, 2020
- 09:00-13:15 (UTC-8)
- 11:00-15:15 (UTC-5)
- 19:00-23:15 (UTC+3)
Preparation / what to install
Most of these can be installed using pip:
- pandas
- torch
- torchaudio
- librosa
- numpy
- jupyter
- coloredlogs
Schedule
All times in UTC-5.
- 11:00 - 11:15 Introductions and installation check
- 11:15 - 11:30 1. Introduction and overview
- 11:30 - 12:15 2. Audio processing(Anurag)
- 12:15 - 12:30 Discussion and break
- 12:30 - 13:15 3. Acoustic models (Nastya)
- 13:15 - 14:00 4. Decoding (Fran)
- 14:00 - 14:15 Discussion and break
- 14:15 - 15:00 5. Language modelling (Nils)
- 15:00 - 15:15 Wrapping up