Llama 3
Meta
partial detail 8 method fields published
Evaluation
Speech generation: text normalization
Effect of Llama 3 embeddings on text normalization with varying right-context (3 TN tokens vs full bidirectional context), comparing models with and without Llama 3 embeddings
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.