DiffSinger icon indicating copy to clipboard operation
DiffSinger copied to clipboard

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

Results 68 DiffSinger issues
Sort by recently updated
recently updated
newest added

Please help, it seems the hparams variable is not accessible from multiprocessing: raceback (most recent call last): File "", line 1, in File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 116, in spawn_main exitcode =...

maybe it's possible to create a google colab?

I just follow all the steps in docs SVS-opencpop-e2e.md. All the data are as following: . |--data |--raw |--opencpop |--segments |--transcriptions.txt |--wavs |--checkpoints |--MY_DS_EXP_NAME (optional) |--0109_hifigan_bigpopcs_hop128 (vocoder) |--model_ckpt_steps_1512000.ckpt |--config.yaml 1)...

Corrects ```source``` to ```conda```

First of all, thanks for this great paper and official open-source code. I want to check demo page which contains DiffSinger and baselines. But I can't access to demo page...

Neither LatestModelCheckpoint nor ModelCheckpoint has the attribute '_save_model' . Where does this attribute come from ? Shall I replace it with '_save_checkpoint' ?

Hi, Thank you for the awesome project! I wonder why the hparam "predictor_grad" is required. Can you explain the reason please? Best regards, Hankyu

want to change the number of Opencpop dataset songs from 100 to 20. When I set the number of songs to 50, everything works fine ![image](https://user-images.githubusercontent.com/55702200/217724619-d3bf32e8-6a99-4c46-b0e8-c01dd58f685b.png) When I set the...

报错OSError: Unable to synchronously open file ,网上也没找到相应的解决方法,更新声码器也没用,打算再重新处理一遍训练集试试 ![屏幕截图 2024-03-31 013714](https://github.com/MoonInTheRiver/DiffSinger/assets/95063623/120054fb-3ca1-4125-9649-6771da5d825b)