Inference not working

[manojkr19]

Hi I'm trying to use a sample to train and inference a text. I got some output in the older version, but after updating to the latest version, it creates an empty audio file. Screenshot of the inference page attached. Since the text is in chinese, I dont know if I'm doing the right thing here. Please hep.

[manojkr19]

This is all I see in the console

0%|▏ | 1/1500 [00:00<06:05, 4.11it/s]T2S Decoding EOS [1604 -> 1605] 0%|▏ | 1/1500 [00:00<06:45, 3.70it/s] huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either:

• Avoid using tokenizers before the fork if possible
• Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) min value is tensor(-1.0733) max value is tensor(1.0073) 1.169 0.852 0.274 0.317

[ISDHN]

Above this page, "模型切换" means "Change Model", and you have selected the pretrained model rather than the model you trained here.

[manojkr19]

I'm sorry if this is a stupid question. my understanding is that

1. I upload sample audio and its text
2. I put the new text and start inference and I get new audio reading out new text.

please help me understand how do I train my model and load it here for inference thanks

[manojkr19]

Hi Can someone please help?

[AWangji]

Hi Can someone please help?

hi, I met the same problem with you. How do you resolve it?