word-language-model

LSTM language model learns to generate Shakespeare-style text

Generated Text

Generated text will appear here after training...

Seed Text

The model will continue from this text

Idle
Epoch 0/50Batch 0-
loss
-
Training Loss
-----StepLoss
-

Hyperparameters

0.0010
50
128
64
0.8

About this example

This character-level LSTM language model learns patterns in Shakespeare's sonnets. After training, it can generate new text in a similar style using the learned sequential patterns.

Temperature controls randomness: lower values produce more predictable text, higher values produce more creative (but potentially nonsensical) output.

Training Corpus

From fairest creatures we desire increase, That thereby beauty's rose might never die, But as the riper should by time decease, His tender heir might bear his memory: But thou contracted to thine own bright eyes, Feed'st thy light's flame with self-substantial fuel, Making a famine where abundance l...

Logs
No output yet...