mrq
/
ai-voice-cloning
31
72
Fork 42
Code Issues 221 Pull Requests 5 Packages Projects Releases Wiki Activity

Update 'Training'

master
mrq 2023-03-12 05:59:16 +07:00
parent 6e880d189a
commit c1fc7d4a66
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Training.md
Unescape Escape

@ -183,7 +183,7 @@ The autoregressive model predicts tokens in as `<speech conditioning>:<text toke
* text tokens (I believe) represents phonemes, which can be compared against the CLVP for "most likely candidates"
* MEL tokens represent the actual speech, which gets later converted to a waveform
Now back to the scope of answering your question. Each curve is responsible for quantifying how accurate the model is.
Each curve is responsible for quantifying how accurate the model is.
* the text loss quantifies how well the predicted text tokens match the source text. This doesn't necessarily need to have too low of a loss. In fact, trainings that have it lower than the mel loss turns out unusuable.
* the mel loss quantifies how well the predicted speech tokens match the source audio. This definitely seems to benefit from low loss rates.
* the total loss is a bit irrelevant, and I should probably hide it since it almost always follows the mel loss, due to how the text loss gets weighed.