Update README.md
Browse files
README.md
CHANGED
@@ -16,9 +16,10 @@ Or use this [bash-script](https://github.com/bene-ges/nemo_compatible/blob/main/
|
|
16 |
### Input
|
17 |
|
18 |
This model is indended to be used in a G2P + FastPitch + HifiGAN pipeline (see above).
|
19 |
-
If run independently, it 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 Russian
|
20 |
If you feed plain text directly, it will work, but quality will be low.
|
21 |
|
|
|
22 |
### Output
|
23 |
|
24 |
This model generates mel spectrograms.
|
|
|
16 |
### Input
|
17 |
|
18 |
This model is indended to be used in a G2P + FastPitch + HifiGAN pipeline (see above).
|
19 |
+
If run independently, it 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 Russian words to phonemes, or this new [IPA-compatible G2P tool](https://github.com/omogr/omogre) that can handle ambiguitity on sentence level.
|
20 |
If you feed plain text directly, it will work, but quality will be low.
|
21 |
|
22 |
+
|
23 |
### Output
|
24 |
|
25 |
This model generates mel spectrograms.
|