Update README.md
Browse files
README.md
CHANGED
|
@@ -99,7 +99,7 @@ As the text sequence length is unknown during inference, a length predictor modu
|
|
| 99 |
##### Length Predictor
|
| 100 |
|
| 101 |
To make TrorYongASR2 as lightweight as possible, length predictor infers the length of text sequence conditioned directly on the audio encoding.
|
| 102 |
-
TrorYongASR2 limits the output text to
|
| 103 |
Therefore, length predictor's head is a linear layer with a softcap as the following:
|
| 104 |
|
| 105 |
$$
|
|
|
|
| 99 |
##### Length Predictor
|
| 100 |
|
| 101 |
To make TrorYongASR2 as lightweight as possible, length predictor infers the length of text sequence conditioned directly on the audio encoding.
|
| 102 |
+
TrorYongASR2 limits the output text to $``448``$ tokens.
|
| 103 |
Therefore, length predictor's head is a linear layer with a softcap as the following:
|
| 104 |
|
| 105 |
$$
|