Different Audio quality among intermediate results

[auspicious3000]

While training the vocoder, it writes to the following three folders "audio", "dev_eval", and "train_no_dev_eval".
The audios inside "dev_eval" and "train_no_dev_eval" all sounds very good. However, the audios inside "audio" all have audible hissing background noise.
What's the difference between those three folders?
Is it possible that the audios written to "audios" folder were somehow generated differently from the ones inside the other two folders?
Thanks!

[r9y9]

In short: the difference is using teacher-forcing generation or not.

• dev_eval: Results for development (validation) set. All waveform is generated by autoregressive generation (i.e. inference mode).
• train_no_dev_eval: Results for training set. All waveform is generated by autoregressive generation (i.e. inference mode).
• audio: Results for training set. All waveform is generated by teacher-forcing generation (i.e. training mode).

[auspicious3000]

Does it make sense that the waveform generated under training mode sounds worse than that generated under inference mode?
I mean, under training mode, since the model has access to the previous ground truth, the output should sound at least as good as the output using inference mode.
What's your opinion on this?
Thanks!