thangquang09/parler-tts-vietnamese-v1-stage2

Full fine-tune vs parler-tts/parler-tts-mini-v1. Fine-tune: 99% of the weights changed, across 24 of 24 layers.

Tensors changed: other 72/217, lm_head 9/9, Embeddings 9/10, Norms 195/195, Attention 289/289, MLP 48/48

On the Hub · Downloads on Model Pulse