Llama 3
Meta
partial detail 13 method fields published
Evaluation
Speech generation: prosody modeling human evaluation
Two sets of human evaluation comparing prosody models (PM) with and without Llama 3 8B embeddings; raters indicate preferences on samples; final waveform via in-house transformer-based acoustic model
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.