Boris Piakillia

High values of WER on Libri Dataset (test-clean and dev-clean)

5

Hi everyone! I have the following problem: when I firstly try to train pure DeepSpeech net with default parameters (7 layers, 1760 neurons, batch size is 20) I always get...

ValueError: y has more than n_class unique elements in Hyperopt Jupyter notebook and accordingly in models.py

3

## 🐛 Bug When you run the code in the `Advanced_model_training_using_hyperopt.ipynb ` ``` validation=dc.models.ValidationCallback(valid_dataset, 1000, [metric],save_dir=save_dir,transformers=transformers,save_on_minimum=False) model.fit(train_dataset, nb_epoch=25,callbacks=validation) ``` you getting error every time you have more than 2 classes...