# Single male speaker

A Russian text-to-speech model trained on the RUSLAN corpus, using FastPitch and HifiGAN architectures, supporting speech synthesis at 22.05kHz sampling rate.

A Russian text-to-speech model trained with the NeMo toolkit, using a combination of G2P phonetic conversion, FastPitch acoustic model, and HifiGAN vocoder to support high-quality Russian speech synthesis.

A Transformer-based text-to-speech model from fairseq S², supporting Russian single male speaker, pre-trained on Common Voice v7 and fine-tuned on CSS10.

Fairseq S^2-based Transformer text-to-speech model supporting Spanish, trained on CSS10 dataset