DiffSinger

DiffSinger copied to clipboard

处理数据的时候报这个问题

2

Traceback (most recent call last): File "/mnt/d/workspace/DiffSinger-master/utils/multiprocess_utils.py", line 13, in chunked_worker res = map_func(*arg) File "/mnt/d/workspace/DiffSinger-master/data_gen/singing/binarize.py", line 382, in process_item cls.get_pitch(wav_fn, wav, mel, ph, res) File "/mnt/d/workspace/DiffSinger-master/data_gen/singing/binarize.py", line 364, in...

wangjiancheng-123

Hi, everyone, I wonder whether there is an open source model for English language Singing Voice synthesis ? Or other models you can recomend?

leffff

如何推理生成音频

1

请问大佬们，我是否可以使用带有歌词的曲谱利用Diffsinger生成音频，可能实现吗？

ghfyyds

Training failed

1

Hello! Can you please help how I can fix this error? ``` Epoch 1: : 0batch [00:00, ?batch/s] Traceback (most recent call last): File "tasks/run.py", line 15, in run_task() File...

Arseny5

运行时配置文件不完整

1

当训练模型或是测试时，keyerror报错，该如何获取完整的配置文件呢？ ![Uploading 1735181995103.png…]()

Charisee-W

Hi, I am training a singing model following this [pipeline](https://github.com/MoonInTheRiver/DiffSinger/blob/05c8353d611e07e6893eff1b8e4ac4224e45b14d/docs/README-SVS-opencpop-cascade.md) with a different dataset. I wonder how to get the predicted K_steps from trained fs model for ds model, rather...

fish0510

adszvlog-cmyk

Letra – “Ajude a Vendedora” Verso Cheguei na rua com meu cooler na mão É garrafa de açaí, direto do coração Feito com carinho, sabor que alimenta Cada compra sua...

danielysilva1212-commits