Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,10 @@ All of the datasets used to train these models are:
|
|
| 22 |
2. These datasets are edited to contain the best high-quality audio of the speaker's voice with no background noise, music, silence, or any artifacts.
|
| 23 |
|
| 24 |
3.The sample rate of all of these datasets are 44100 hz with the training using the 48k hz.
|
| 25 |
-
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
Training:
|
| 28 |
|
|
|
|
| 22 |
2. These datasets are edited to contain the best high-quality audio of the speaker's voice with no background noise, music, silence, or any artifacts.
|
| 23 |
|
| 24 |
3.The sample rate of all of these datasets are 44100 hz with the training using the 48k hz.
|
| 25 |
+
|
| 26 |
+
4. For the dataset recording and extraction process sometimes it may not be 100% perfect due to background noise or music interfering and in some cases
|
| 27 |
+
I may not even reach to the 20-25 minute mark since there may be very little or no data available, as such I also reduce the number of epochs to 200 to
|
| 28 |
+
prevent overtraining and achieve the highest quality with minimal dataset length.
|
| 29 |
|
| 30 |
Training:
|
| 31 |
|