Update README.md
Browse files
README.md
CHANGED
@@ -37,7 +37,7 @@ When using this model, make sure that your speech input is sampled at 16kHz.
|
|
37 |
# Performance\*
|
38 |
|
39 |
![Comparison](comparison.png "Comparison")
|
40 |
-
|
41 |
|
42 |
## Training
|
43 |
This model has been fine-tuned for 120000 updates on NST + CommonVoice and then for an additional 20000 updates on CommonVoice only. The additional fine-tuning on CommonVoice hurts performance on the NST+CommonVoice test set somewhat and, unsurprisingly, improves it on the CommonVoice test set. It seems to perform generally better though [citation needed].
|
|
|
37 |
# Performance\*
|
38 |
|
39 |
![Comparison](comparison.png "Comparison")
|
40 |
+
<center>\*<i>Chart shows performance without the additional 20k steps of Common Voice fine-tuning</i></center>
|
41 |
|
42 |
## Training
|
43 |
This model has been fine-tuned for 120000 updates on NST + CommonVoice and then for an additional 20000 updates on CommonVoice only. The additional fine-tuning on CommonVoice hurts performance on the NST+CommonVoice test set somewhat and, unsurprisingly, improves it on the CommonVoice test set. It seems to perform generally better though [citation needed].
|