title: 'DiffSinger'
description: |
  This model is trained on 5 hours single female singing voice samples of Opencpop dataset. (该模型在开源数据集Opencpop的5小时单人歌声上训练。)

  Please assign pitch and duration values to each Chinese character. The corresponding pitch and duration value of each character should be separated by a | separator. It is necessary to ensure that the note window separated by the separator is consistent with the number of Chinese characters (AP or SP is also viewed as a Chinese character). (请给每个汉字分配音高和时值, 每个字对应的音高和时值需要用|分隔符隔开。需要保证分隔符分割出来的音符窗口与汉字个数(AP或SP也算一个汉字)一致。)

  You can click one of the examples to load them. (你可以点击下方示例，加载示例曲谱。)

  Note: This space is running on CPU, inference times will be higher. (该Demo是在Huggingface提供的CPU上运行的, 其推理速度在本地会更高一些。)

article: |
  Link to <a href='https://github.com/MoonInTheRiver/DiffSinger' style='color:blue;' target='_blank\'>Github REPO</a>
example_inputs:
  - |-
    你 说 你 不 SP 懂 为 何 在 这 时 牵 手 AP<sep>D#4/Eb4 | D#4/Eb4 | D#4/Eb4 | D#4/Eb4 | rest | D#4/Eb4 | D4 | D4 | D4 | D#4/Eb4 | F4 | D#4/Eb4 | D4 | rest<sep>0.113740 | 0.329060 | 0.287950 | 0.133480 | 0.150900 | 0.484730 | 0.242010 | 0.180820 | 0.343570 | 0.152050 | 0.266720 | 0.280310 | 0.633300 | 0.444590
  - |-
    小酒窝长睫毛AP是你最美的记号<sep>C#4/Db4 | F#4/Gb4 | G#4/Ab4 | A#4/Bb4 F#4/Gb4 | F#4/Gb4 C#4/Db4 | C#4/Db4 | rest | C#4/Db4 | A#4/Bb4 | G#4/Ab4 | A#4/Bb4 | G#4/Ab4 | F4 | C#4/Db4<sep>0.407140 | 0.376190 | 0.242180 | 0.509550 0.183420 | 0.315400 0.235020 | 0.361660 | 0.223070 | 0.377270 | 0.340550 | 0.299620 | 0.344510 | 0.283770 | 0.323390 | 0.360340

#inference_cls: inference.svs.ds_cascade.DiffSingerCascadeInfer
#exp_name: 0303_opencpop_ds58_midi

inference_cls: inference.svs.ds_e2e.DiffSingerE2EInfer
exp_name: 0228_opencpop_ds100_rel