emphasis note
Browse files
README.md
CHANGED
@@ -41,7 +41,11 @@ datasets:
|
|
41 |
- ylacombe/expresso
|
42 |
base_model: Pendrokar/xvapitch
|
43 |
---
|
44 |
-
xVASynth's xVAPitch (v3) type of voice models based on the Expresso dataset. Without enunciated, laughing, whispering and singing styles.
|
|
|
|
|
|
|
|
|
45 |
|
46 |
ex01 male: <audio controls>
|
47 |
<source src="https://huggingface.co/Pendrokar/xvapitch_expresso/resolve/main/x_ex01.wav?download=true" type="audio/wav">
|
|
|
41 |
- ylacombe/expresso
|
42 |
base_model: Pendrokar/xvapitch
|
43 |
---
|
44 |
+
xVASynth's xVAPitch (v3) type of voice models based on the Expresso dataset. Without enunciated, laughing, whispering and singing styles. From the `confused` style, only questions were used.
|
45 |
+
|
46 |
+
These models can also do emphasis on words by using colons `:`, rather than the typical quotemarks `"` which are skipped by the xVASynth text pre-processor:
|
47 |
+
* What :exactly: is it?
|
48 |
+
* Well :normally: we just let it run.
|
49 |
|
50 |
ex01 male: <audio controls>
|
51 |
<source src="https://huggingface.co/Pendrokar/xvapitch_expresso/resolve/main/x_ex01.wav?download=true" type="audio/wav">
|