Update README.md
Browse files
README.md
CHANGED
|
@@ -53,12 +53,13 @@ The model utilizes a three-step approach to audio processing:
|
|
| 53 |
https://www.outeai.com/blog/OuteTTS-0.1-350M
|
| 54 |
|
| 55 |
## Limitations
|
|
|
|
| 56 |
|
| 57 |
- Vocabulary constraints due to training data limitations
|
| 58 |
- String-only input support
|
| 59 |
- Given its compact 350M parameter size, the model may frequently alter, insert, or omit wrong words, leading to variations in output quality.
|
| 60 |
- Variable temperature sensitivity depending on use case
|
| 61 |
-
- Performs best with shorter sentences, as accuracy may decrease with longer inputs
|
| 62 |
|
| 63 |
### Speech Samples
|
| 64 |
|
|
|
|
| 53 |
https://www.outeai.com/blog/OuteTTS-0.1-350M
|
| 54 |
|
| 55 |
## Limitations
|
| 56 |
+
Being an experimental v0.1 release, there are some known issues:
|
| 57 |
|
| 58 |
- Vocabulary constraints due to training data limitations
|
| 59 |
- String-only input support
|
| 60 |
- Given its compact 350M parameter size, the model may frequently alter, insert, or omit wrong words, leading to variations in output quality.
|
| 61 |
- Variable temperature sensitivity depending on use case
|
| 62 |
+
- Performs best with shorter sentences, as accuracy may decrease with longer inputs
|
| 63 |
|
| 64 |
### Speech Samples
|
| 65 |
|