Haven

> Authors used 300k steps with batch = 64, start from that. @nikich340 Authors used 300k steps with batch = 64, start from that. My batch_size=8; Do I need to...

@athenasaurav Ok, I see what you mean. Thank you very much for your answer!

> 我能够对部分数据进行（无条件）训练，并且能够生成语音……但无论如何，它只能生成一个单词。我很快就会研究条件训练。 @deepglugs Hello, have you studied conditioning? I found that I couldn't generate hints and text. If you have any relevant experience, please let me know

@15755841658 Have you solved the problem? My VCTK dataset also doesn't have '_mic2.flac'. How should I solve it?

I have the same confusion, I also want to use my data to retrain a hifigan vocoder suitable for this model.

> thank you very much

@Zain-Jiang Hi, I would like to ask how to use other data to fine-tune the vocoder or retrain the vocoder.Thanks!

May I ask if you have solved the problem？ I used pre-trained models for inference and still ran into a lot of problems

Hi, @Zain-Jiang 1. I downloaded the relevant documents you provided from this link `https://drive.google.com/drive/folders/1H-dk7cNYVn1DSzYq_q66rS5b5xpbdBi4?usp=sharing` to complete the inference step. 2. Based on my experiments, it seems that `phone_set.json, spk_map.json, word_set.json`needs...

@Zain-Jiang Yes, you are right. I found no hparams['diff_decoder_type'] in `config.yaml`. They are in `spec_denoiser_libritts.yaml`. So maybe we need to load `spec_denoiser_libritts.yaml` instead of the default `config.yaml`?