bene-ges/

tts_ru_ipa_fastpitch_ruslan

See example of inference pipeline for Russian TTS (G2P + FastPitch + HifiGAN) in this notebook. Or use this bash-script.

This model is indended to be used in a G2P + FastPitch + HifiGAN pipeline (see above). If run independently, it expects text converted to IPA-like transcriptions. See this g2p model for conversion of plain Russian words to phonemes, or this new IPA-compatible G2P tool that can handle ambiguitity on sentence level. If you feed plain text directly, this FastPitch model will work, but quality will be low.

This model generates mel spectrograms.

The NeMo toolkit [1] was used for training the model for 1000+ epochs. Full training script is here

This model is trained on RUSLAN [2] corpus (single speaker, male voice) sampled at 22050Hz.