Add sharing function

checkpoints/m4singer_diff_e2e/config.yaml

@@ -105,7 +105,7 @@ pitch_extractor: parselmouth
 pitch_loss: l1
 pitch_norm: log
 pitch_type: frame
-pndm_speedup: 20
+pndm_speedup: 5
 pre_align_args:
   allow_no_txt: false
   denoise: false

inference/m4singer/gradio/gradio_settings.yaml

@@ -1,13 +1,18 @@
 title: 'M4Singer'
 description: |
-  This page aims to display the SVS function of M4Singer. SingerID can be switched freely to preview the timbre of each singer. Click examples below to quickly load scores and audio. （本页面为M4Singer歌声合成功能展示。SingerID可以自由切换用以预览各歌手的音色。点击下方Examples可以快速加载乐谱和音频。）
+  This page aims to display the singing voice synthesis function of M4Singer. SingerID can be switched freely to preview the timbre of each singer. Click examples below to quickly load scores and audio.
+   (本页面为M4Singer歌声合成功能展示。SingerID可以自由切换用以预览各歌手的音色。点击下方Examples可以快速加载乐谱和音频。)
 
-  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。)
+  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 (aspirate) or SP (silence) 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一致。换气或静音符也算一个汉字。)
+
+  The notes corresponding to AP and SP are fixed as rest. If there are multiple notes in a window (| .... |), it means that the Chinese character corresponding to the window is glissando, and each note needs to be assigned a duration.
+   (AP和SP对应的音符固定为rest。若一个窗口(| .... |)内有多个音符, 代表该窗口对应的汉字为滑音, 需要为每个音符都分配时长。)
 
-  Note: This page is running on CPU, please refer to github for the local running solutions.（注意：本页面使用CPU推理，本地运行方案请参考<a href='https://github.com/M4Singer/M4Singer' style='color:blue;' target='_blank\'>Github REPO</a>。）
 article: |
-  Link to <a href='https://github.com/M4Singer/M4Singer' style='color:blue;' target='_blank\'>Github REPO</a>
+  Note: This page is running on CPU, please refer to <a href='https://github.com/M4Singer/M4Singer' style='color:blue;' target='_blank\'>Github REPO</a> for the local running solutions and for our dataset.
 
+  --------
   If our work is useful for your research, please consider citing:
   ```bibtex
   @inproceedings{

inference/m4singer/gradio/infer.py

@@ -3,20 +3,13 @@ import re
 
 import gradio as gr
 import yaml
-from gradio.inputs import Textbox, Dropdown
+from gradio.components import Textbox, Dropdown
 
 from inference.m4singer.base_svs_infer import BaseSVSInfer
 from utils.hparams import set_hparams
 from utils.hparams import hparams as hp
 import numpy as np
-import torch, random
-
-def setup_seed(seed):
-    torch.manual_seed(seed)
-    torch.cuda.manual_seed_all(seed)
-    np.random.seed(seed)
-    random.seed(seed)
-    torch.backends.cudnn.deterministic = True
+from inference.m4singer.gradio.share_btn import community_icon_html, loading_icon_html, share_js
 
 class GradioInfer:
     def __init__(self, exp_name, inference_cls, title, description, article, example_inputs):
@@ -61,11 +54,10 @@ class GradioInfer:
                 s = ""
                 n = ""
         audio_outs = np.concatenate(audio_outs)
-        return hp['audio_sample_rate'], audio_outs
+        return (hp['audio_sample_rate'], audio_outs), gr.update(visible=True), gr.update(visible=True), gr.update(visible=True)
 
     def run(self):
         set_hparams(config=f'checkpoints/{self.exp_name}/config.yaml', exp_name=self.exp_name, print_hparams=False)
-        #setup_seed(1234)
         infer_cls = self.inference_cls
         self.infer_ins: BaseSVSInfer = infer_cls(hp)
         example_inputs = self.example_inputs
@@ -81,21 +73,68 @@ class GradioInfer:
             'Bass-1',  'Bass-2',  'Bass-3',
             ]
 
-        iface = gr.Interface(fn=self.greet,
-                             inputs=[
-                                 Dropdown(choices=singerList, default=example_inputs[0][0], label="SingerID"),
-                                 Textbox(lines=2, placeholder=None, default=example_inputs[0][1], label="input text"),
-                                 Textbox(lines=2, placeholder=None, default=example_inputs[0][2], label="input note"),
-                                 Textbox(lines=2, placeholder=None, default=example_inputs[0][3], label="input duration")]
-                             ,
-                             outputs="audio",
-                             allow_flagging="never",
-                             title=self.title,
-                             description=self.description,
-                             article=self.article,
-                             examples=example_inputs,
-                             enable_queue=True)
-        iface.launch(share=False)# cache_examples=True)
+        css = """
+        #share-btn-container {
+            display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem;
+        }
+        #share-btn {
+            all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;right:0;
+        }
+        #share-btn * {
+            all: unset;
+        }
+        #share-btn-container div:nth-child(-n+2){
+            width: auto !important;
+            min-height: 0px !important;
+        }
+        #share-btn-container .wrap {
+            display: none !important;
+        }
+        """
+        with gr.Blocks(css=css) as demo:
+            gr.HTML("""<div style="text-align: center; margin: 0 auto;">
+                          <div
+                          style="
+                              display: inline-flex;
+                              align-items: center;
+                              gap: 0.8rem;
+                              font-size: 1.75rem;
+                          "
+                          >
+                          <h1 style="font-weight: 900; margin-bottom: 10px; margin-top: 14px;">
+                              M4Singer
+                          </h1>
+                          </div>
+                        </div>
+                        """
+                    )
+            gr.Markdown(self.description)
+            with gr.Row():
+                with gr.Column():
+                    singer_l = Dropdown(choices=singerList, value=example_inputs[0][0], label="SingerID", elem_id="inp_singer")
+                    inp_text = Textbox(lines=2, placeholder=None, value=example_inputs[0][1], label="input text", elem_id="inp_text")
+                    inp_note = Textbox(lines=2, placeholder=None, value=example_inputs[0][2], label="input note", elem_id="inp_note")
+                    inp_duration = Textbox(lines=2, placeholder=None, value=example_inputs[0][3], label="input duration", elem_id="inp_duration")
+                    generate = gr.Button("Generate Singing Voice from Musical Score")
+                with gr.Column(lem_id="col-container"):
+                    singing_output = gr.Audio(label="Result", type="numpy", elem_id="music-output")
+
+                    with gr.Group(elem_id="share-btn-container"):
+                        community_icon = gr.HTML(community_icon_html, visible=False)
+                        loading_icon = gr.HTML(loading_icon_html, visible=False)
+                        share_button = gr.Button("Share to community", elem_id="share-btn", visible=False)
+            gr.Examples(examples=self.example_inputs,
+                        inputs=[singer_l, inp_text, inp_note, inp_duration],
+                        outputs=[singing_output, share_button, community_icon, loading_icon],
+                        fn=self.greet,
+                        cache_examples=True)
+            gr.Markdown(self.article)
+            generate.click(self.greet,
+                               inputs=[singer_l, inp_text, inp_note, inp_duration],
+                               outputs=[singing_output, share_button, community_icon, loading_icon],)
+            share_button.click(None, [], [], _js=share_js)
+        demo.queue(max_size=32, concurrency_count=20).launch(share=False)
+
 
 if __name__ == '__main__':
     gradio_config = yaml.safe_load(open('inference/m4singer/gradio/gradio_settings.yaml'))

inference/m4singer/gradio/share_btn.py

@@ -0,0 +1,86 @@
+community_icon_html = """<svg id="share-btn-share-icon" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32">
+    <path d="M20.6081 3C21.7684 3 22.8053 3.49196 23.5284 4.38415C23.9756 4.93678 24.4428 5.82749 24.4808 7.16133C24.9674 7.01707 25.4353 6.93643 25.8725 6.93643C26.9833 6.93643 27.9865 7.37587 28.696 8.17411C29.6075 9.19872 30.0124 10.4579 29.8361 11.7177C29.7523 12.3177 29.5581 12.8555 29.2678 13.3534C29.8798 13.8646 30.3306 14.5763 30.5485 15.4322C30.719 16.1032 30.8939 17.5006 29.9808 18.9403C30.0389 19.0342 30.0934 19.1319 30.1442 19.2318C30.6932 20.3074 30.7283 21.5229 30.2439 22.6548C29.5093 24.3704 27.6841 25.7219 24.1397 27.1727C21.9347 28.0753 19.9174 28.6523 19.8994 28.6575C16.9842 29.4379 14.3477 29.8345 12.0653 29.8345C7.87017 29.8345 4.8668 28.508 3.13831 25.8921C0.356375 21.6797 0.754104 17.8269 4.35369 14.1131C6.34591 12.058 7.67023 9.02782 7.94613 8.36275C8.50224 6.39343 9.97271 4.20438 12.4172 4.20438H12.4179C12.6236 4.20438 12.8314 4.2214 13.0364 4.25468C14.107 4.42854 15.0428 5.06476 15.7115 6.02205C16.4331 5.09583 17.134 4.359 17.7682 3.94323C18.7242 3.31737 19.6794 3 20.6081 3ZM20.6081 5.95917C20.2427 5.95917 19.7963 6.1197 19.3039 6.44225C17.7754 7.44319 14.8258 12.6772 13.7458 14.7131C13.3839 15.3952 12.7655 15.6837 12.2086 15.6837C11.1036 15.6837 10.2408 14.5497 12.1076 13.1085C14.9146 10.9402 13.9299 7.39584 12.5898 7.1776C12.5311 7.16799 12.4731 7.16355 12.4172 7.16355C11.1989 7.16355 10.6615 9.33114 10.6615 9.33114C10.6615 9.33114 9.0863 13.4148 6.38031 16.206C3.67434 18.998 3.5346 21.2388 5.50675 24.2246C6.85185 26.2606 9.42666 26.8753 12.0653 26.8753C14.8021 26.8753 17.6077 26.2139 19.1799 25.793C19.2574 25.7723 28.8193 22.984 27.6081 20.6107C27.4046 20.212 27.0693 20.0522 26.6471 20.0522C24.9416 20.0522 21.8393 22.6726 20.5057 22.6726C20.2076 22.6726 19.9976 22.5416 19.9116 22.222C19.3433 20.1173 28.552 19.2325 27.7758 16.1839C27.639 15.6445 27.2677 15.4256 26.746 15.4263C24.4923 15.4263 19.4358 19.5181 18.3759 19.5181C18.2949 19.5181 18.2368 19.4937 18.2053 19.4419C17.6743 18.557 17.9653 17.9394 21.7082 15.6009C25.4511 13.2617 28.0783 11.8545 26.5841 10.1752C26.4121 9.98141 26.1684 9.8956 25.8725 9.8956C23.6001 9.89634 18.2311 14.9403 18.2311 14.9403C18.2311 14.9403 16.7821 16.496 15.9057 16.496C15.7043 16.496 15.533 16.4139 15.4169 16.2112C14.7956 15.1296 21.1879 10.1286 21.5484 8.06535C21.7928 6.66715 21.3771 5.95917 20.6081 5.95917Z" fill="#FF9D00"></path>
+    <path d="M5.50686 24.2246C3.53472 21.2387 3.67446 18.9979 6.38043 16.206C9.08641 13.4147 10.6615 9.33111 10.6615 9.33111C10.6615 9.33111 11.2499 6.95933 12.59 7.17757C13.93 7.39581 14.9139 10.9401 12.1069 13.1084C9.29997 15.276 12.6659 16.7489 13.7459 14.713C14.8258 12.6772 17.7747 7.44316 19.304 6.44221C20.8326 5.44128 21.9089 6.00204 21.5484 8.06532C21.188 10.1286 14.795 15.1295 15.4171 16.2118C16.0391 17.2934 18.2312 14.9402 18.2312 14.9402C18.2312 14.9402 25.0907 8.49588 26.5842 10.1752C28.0776 11.8545 25.4512 13.2616 21.7082 15.6008C17.9646 17.9393 17.6744 18.557 18.2054 19.4418C18.7372 20.3266 26.9998 13.1351 27.7759 16.1838C28.5513 19.2324 19.3434 20.1173 19.9117 22.2219C20.48 24.3274 26.3979 18.2382 27.6082 20.6107C28.8193 22.9839 19.2574 25.7722 19.18 25.7929C16.0914 26.62 8.24723 28.3726 5.50686 24.2246Z" fill="#FFD21E"></path>
+</svg>"""
+
+loading_icon_html = """<svg id="share-btn-loading-icon" style="display:none;" class="animate-spin"
+   style="color: #ffffff; 
+"
+   xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" fill="none" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><circle style="opacity: 0.25;" cx="12" cy="12" r="10" stroke="white" stroke-width="4"></circle><path style="opacity: 0.75;" fill="white" d="M4 12a8 8 0 018-8V0C5.373 0 0 5.373 0 12h4zm2 5.291A7.962 7.962 0 014 12H0c0 3.042 1.135 5.824 3 7.938l3-2.647z"></path></svg>"""
+
+share_js = """async () => {
+	async function uploadFile(file){
+		const UPLOAD_URL = 'https://huggingface.co/uploads';
+		const response = await fetch(UPLOAD_URL, {
+			method: 'POST',
+			headers: {
+				'Content-Type': file.type,
+				'X-Requested-With': 'XMLHttpRequest',
+			},
+			body: file, /// <- File inherits from Blob
+		});
+		const url = await response.text();
+		return url;
+	}
+
+    async function getOutputMusicFile(audioEL){
+        const res = await fetch(audioEL.src);
+        const blob = await res.blob();
+        const audioId = Date.now() % 200;
+        const fileName = `SVS-${{audioId}}.wav`;
+        const musicBlob = new File([blob], fileName, { type: 'audio/wav' });
+        return musicBlob;
+	}
+
+    const gradioEl = document.querySelector('body > gradio-app');
+
+    //const gradioEl = document.querySelector("gradio-app").shadowRoot;
+    const inputSinger = gradioEl.querySelector('#inp_singer select').value;
+    const inputText = gradioEl.querySelector('#inp_text textarea').value;
+    const inputNote = gradioEl.querySelector('#inp_note textarea').value;
+    const inputDuration = gradioEl.querySelector('#inp_duration textarea').value;
+    const outputMusic = gradioEl.querySelector('#music-output audio');
+    const outputMusic_src = gradioEl.querySelector('#music-output audio').src;
+    
+    const outputMusic_name = outputMusic_src.split('/').pop();
+    let titleTxt = outputMusic_name;
+    //if(titleTxt.length > 100){
+    //    titleTxt = titleTxt.slice(0, 100) + ' ...';
+    //}
+    const shareBtnEl = gradioEl.querySelector('#share-btn');
+    const shareIconEl = gradioEl.querySelector('#share-btn-share-icon');
+    const loadingIconEl = gradioEl.querySelector('#share-btn-loading-icon');
+    if(!outputMusic){
+        return;
+    };
+    shareBtnEl.style.pointerEvents = 'none';
+    shareIconEl.style.display = 'none';
+    loadingIconEl.style.removeProperty('display');
+    const musicFile = await getOutputMusicFile(outputMusic);
+    const dataOutputMusic = await uploadFile(musicFile);
+    const descriptionMd = `#### Input Musical Score:
+${inputSinger}
+
+${inputText}
+
+${inputNote}
+
+${inputDuration}
+    
+#### Singing Voice:
+    
+<audio controls>
+    <source src="${dataOutputMusic}" type="audio/wav">
+Your browser does not support the audio element.
+</audio>
+`;
+    const params = new URLSearchParams({
+        title: titleTxt,
+        description: descriptionMd,
+    });
+	const paramsStr = params.toString();
+	window.open(`https://huggingface.co/spaces/zlc99/M4Singer/discussions/new?${paramsStr}`, '_blank');
+    shareBtnEl.style.removeProperty('pointer-events');
+    shareIconEl.style.removeProperty('display');
+    loadingIconEl.style.display = 'none';
+}"""