1. add huggingface SVS; 2. add inference logic from raw inputs; 3. update readme.

Author: MoonInTheRiver

README.md

@@ -20,7 +20,7 @@ This repository is the official PyTorch implementation of our AAAI-2022 [paper](
 </table>
 
 :tada: :tada: :tada: **Updates**:
- - Jul.27, 2022: Update documents for [SVS](docs/README-SVS.md). Add [inference logic from raw input](docs/README-SVS-opencpop-cascade.md#4-inference-from-raw-inputs) for SVS; Add Interactive SVS running on [HuggingFace🤗 SVS](https://huggingface.co/spaces/Silentlin/DiffSinger).
+ - Jul.27, 2022: Update documents for [SVS](docs/README-SVS.md). Add [easy inference](docs/README-SVS-opencpop-cascade.md#4-inference-from-raw-inputs); Add Interactive SVS running on [HuggingFace🤗 SVS](https://huggingface.co/spaces/Silentlin/DiffSinger).
  - Mar.2, 2022: MIDI-B-version.
  - Mar.1, 2022: [NeuralSVB](https://github.com/MoonInTheRiver/NeuralSVB), for singing voice beautifying, has been released.
  - Feb.13, 2022: [NATSpeech](https://github.com/NATSpeech/NATSpeech), the improved code framework, which contains the implementations of DiffSpeech and our NeurIPS-2021 work [PortaSpeech](https://openreview.net/forum?id=xmJsuh8xlq) has been released. 

docs/README-SVS.md

@@ -51,7 +51,7 @@ Thus, the pipeline of [2.B](README-SVS-opencpop-e2e.md) can be summarized as:
 Click here for detailed instructions: [link](README-SVS-opencpop-e2e.md).
 
 ### FAQ
-Q: Why do you need F0 in Vocoders?
+Q: Why do I need F0 in Vocoders?
 
 A: See vocoder parts in HiFiSinger, DiffSinger or SingGAN. This is a common practice now.
 
@@ -63,4 +63,8 @@ Q: Why " 'HifiGAN' object has no attribute 'model' "?
 
 A: Please put the pretrained vocoders in your `checkpoints` dictionary.
 
+Q: How to check whether I use GT information or predicted information during inference?
+
+A: Please see codes [here](https://github.com/MoonInTheRiver/DiffSinger/blob/55e2f46068af6e69940a9f8f02d306c24a940cab/tasks/tts/fs2.py#L343). If you set `use_gt_xx=False`, then guess what :) .
+
 ...