New code walkthrough on http://keras.io : speech recognition with Transformer. Very readable and concise demonstration of how to build and train a speech recognition model on the LJSpeech dataset.https://keras.io/examples/audio/transformer_asr/ …
-
-
Then it defines a Transformer encoder, which is your usual Transformer block, as well as a Transformer decoder, which is also your usual Transformer block, but with causal attention to prevent later timesteps to influence the decoding of earlier timesteps.pic.twitter.com/Ige93alEwK
Show this thread -
Finally, it combines the encoder and decoder in a Model subclass, where training logic is packaged in the `train_step()` method (this enables training via `fit()`, which gives you callbacks and distribution support for free). Also note the `generate()` method for inference!pic.twitter.com/cG6KkgUNNO
Show this thread
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.