Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ it can detect, transcribe and do the following:
|
|
| 25 |
a Grapheme decoder head (i.e outputting normal Japanese) will probably be trained as well. Though going directly from audio to Phonemes will result in a
|
| 26 |
more accurate representation for Japanese.
|
| 27 |
|
| 28 |
-
|
| 29 |
|
| 30 |
## Inference and Post-proc (Highly recommended to check the notebook below!)
|
| 31 |
|
|
|
|
| 25 |
a Grapheme decoder head (i.e outputting normal Japanese) will probably be trained as well. Though going directly from audio to Phonemes will result in a
|
| 26 |
more accurate representation for Japanese.
|
| 27 |
|
| 28 |
+
Don't use this model without the post processing functions I wrote below, or you'll get less than ideal performance. check the notebook.
|
| 29 |
|
| 30 |
## Inference and Post-proc (Highly recommended to check the notebook below!)
|
| 31 |
|