|
--- |
|
library_name: fairseq |
|
task: text-to-speech |
|
tags: |
|
- fairseq |
|
- audio |
|
- text-to-speech |
|
language: mn |
|
datasets: |
|
- mbspeech |
|
--- |
|
# tts_transformer-mn-mbspeech |
|
[Transformer](https://arxiv.org/abs/1809.08895) text-to-speech model from fairseq S^2 ([paper](https://arxiv.org/abs/2109.06912)/[code](https://github.com/pytorch/fairseq/tree/main/examples/speech_synthesis)): |
|
- Mongolian |
|
- Single-speaker male voice |
|
- Trained on [MBSpeech](https://github.com/tugstugi/mongolian-nlp/blob/master/datasets/MBSpeech-1.0-csv.zip) |
|
|
|
|
