ddd commited on
Commit
2147060
1 Parent(s): c59ac2d

fix gradio on space

Browse files
inference/svs/gradio/gradio_settings.yaml CHANGED
@@ -2,21 +2,13 @@ title: 'DiffSinger'
2
  description: |
3
  Gradio demo for DiffSinger.
4
 
5
- This model is trained on 5 hours single female singing voice samples of Opencpop dataset.
6
 
7
- (该模型在开源数据集Opencpop的5小时单人歌声上训练。)
8
 
9
- 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 a Chinese character).
10
 
11
- (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。)
12
-
13
- The third example exhibits pitch value changing (C#4->C5).
14
-
15
- (第三个例子演示了乐谱变动 (C#4->C5)。)
16
-
17
- Note: This space is running on CPU, inference times will be higher.
18
-
19
- (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)
20
 
21
  article: |
22
  Link to <a href='https://github.com/MoonInTheRiver/DiffSinger' style='color:blue;' target='_blank\'>Github REPO</a>
@@ -25,8 +17,7 @@ example_inputs:
25
  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
26
  - |-
27
  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
28
- - |-
29
- 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 | C5<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
30
  #inference_cls: inference.svs.ds_cascade.DiffSingerCascadeInfer
31
  #exp_name: 0303_opencpop_ds58_midi
32
 
 
2
  description: |
3
  Gradio demo for DiffSinger.
4
 
5
+ 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。)
6
 
7
+ 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 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。)
8
 
9
+ 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。)
10
 
11
+ 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。)
 
 
 
 
 
 
 
 
12
 
13
  article: |
14
  Link to <a href='https://github.com/MoonInTheRiver/DiffSinger' style='color:blue;' target='_blank\'>Github REPO</a>
 
17
  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
18
  - |-
19
  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
20
+
 
21
  #inference_cls: inference.svs.ds_cascade.DiffSingerCascadeInfer
22
  #exp_name: 0303_opencpop_ds58_midi
23