bene-ges's picture
Update README.md
84f8b98
|
raw
history blame
1.16 kB
metadata
license: cc-by-4.0
language:
  - ru
library_name: nemo

How to use

See example of inference pipeline for G2P + FastPitch + HifiGAN in this notebook.

Input

This model expects text converted to IPA-like transcriptions. See this g2p model for conversion of plain Russian text to phonemes. If you feed plain text directly, it will work, but quality will be low.

Output

This model generates mel spectrograms.

Training

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

Datasets

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

References

  • [1] NVIDIA NeMo Toolkit
  • [2] Gabdrakhmanov L., Garaev R., Razinkov E. (2019) RUSLAN: Russian Spoken Language Corpus for Speech Synthesis. In: Salah A., Karpov A., Potapova R. (eds) Speech and Computer. SPECOM 2019. Lecture Notes in Computer Science, vol 11658. Springer, Cham