Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,28 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-4.0
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-4.0
|
| 3 |
+
language:
|
| 4 |
+
- ru
|
| 5 |
+
library_name: nemo
|
| 6 |
---
|
| 7 |
+
|
| 8 |
+
### Input
|
| 9 |
+
|
| 10 |
+
This model expects text converted to IPA-like transcriptions. See this [g2p model](https://huggingface.co/bene-ges/ru_g2p_ipa_bert_large) for conversion of plain text to phonemes.
|
| 11 |
+
If you feed plain text directly, it will work, but quality will be low.
|
| 12 |
+
|
| 13 |
+
### Output
|
| 14 |
+
|
| 15 |
+
This model generates mel spectrograms.
|
| 16 |
+
|
| 17 |
+
## Training
|
| 18 |
+
|
| 19 |
+
The NeMo toolkit [1] was used for training the model for 1000+ epochs.
|
| 20 |
+
|
| 21 |
+
### Datasets
|
| 22 |
+
|
| 23 |
+
This model is trained on [RUSLAN](https://ruslan-corpus.github.io/) [2] corpus sampled at 22050Hz.
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
## References
|
| 27 |
+
- [1] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
|
| 28 |
+
- [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
|