lidbox
Notebook as HTML | Description |
---|---|
common-voice-small |
Classifying 4 languages from the Mozilla Common Voice dataset |
common-voice-augmenting |
Repeating example 1 with speech data augmentation |
common-voice-embeddings |
Using the trained model from example 2 as a language vector extractor for a back-end classifier |
common-voice-angular-lstm |
Training a language vector model with a dedicated, angular proximity loss function to maximize distance between vectors from different languages |