https://github.com/swamikannan/automatic-shakespeare
Auto-generated text based on Shakespeare poetry
https://github.com/swamikannan/automatic-shakespeare
character-encoding lstm next-character-prediction pytorch pytorch-implementation shakespeare-plays
Last synced: about 1 month ago
JSON representation
Auto-generated text based on Shakespeare poetry
- Host: GitHub
- URL: https://github.com/swamikannan/automatic-shakespeare
- Owner: SwamiKannan
- License: mit
- Created: 2022-09-06T04:57:28.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2022-10-25T14:54:09.000Z (over 3 years ago)
- Last Synced: 2025-03-03T16:49:02.016Z (over 1 year ago)
- Topics: character-encoding, lstm, next-character-prediction, pytorch, pytorch-implementation, shakespeare-plays
- Language: Jupyter Notebook
- Homepage:
- Size: 37.2 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: Readme.md
- License: license
Awesome Lists containing this project
README
# Next character prediction: Shakespeare
## Data:
The data consists of 39 Shakespeare plays and plays written by other Elizabethan-era playwrights, all of which were downloaded as .txt files directly from Project Gutenberg.
The data only contains all the plays of Shakespeare without any labels
## Data Reference:
The Complete Works of Shakespeare [http://www.nzdl.org/cgi-bin/library.cgi?e=q-00000-00---off-0gberg--00-0----0-10-0---0---0direct-10---4-----dtt--0-1l--11-en-50---20-about-shakespeare--00-0-1-00-0-0-11-1-0utfZz-8-10&a=d&c=gberg&srp=0&srn=0&cl=search&d=HASH5dd34b413454f23260c776]
## Dataset:
https://github.com/SwamiKannan/Natural-Language-Processing/blob/main/Shakespeare/shakespeare.txt
## Key Asks:
• Create a language representation model based on Shakespeare text by creating a character prediction tool i.e. P(next character | previous set of characters) using an RNN