Hugging Face's logo

Spaces:
yuekai
/
valle-libritts-demo
Running

App Files Community
Yuekai Zhang commited on
Commit
39eebc7
•
1 Parent(s): 4a0a58a

update index

Browse files
Files changed (1) hide show
  1. index.html +21 -11
index.html CHANGED
@@ -40,7 +40,7 @@
40
  In addition, we find VALL-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis.
41
  </p>
42
 
43
- <br>
44
  official demo page: <a href="https://valle-demo.github.io/">https://valle-demo.github.io</a>
45
  <br>
46
 
@@ -48,9 +48,9 @@
48
  my implementation: <a href="https://github.com/lifeiteng/vall-e">https://github.com/lifeiteng/vall-e</a>
49
  <br><br>
50
  This page is for showing reproduced results only, I keep the main parts of the official demo.
51
- <br><br>
52
 
53
- <h2 id="model-configs" style="text-align: center;">Model Configs</h2>
54
  <div class="table-responsive pt-3">
55
  <table class="table table-hover pt-2">
56
  <thead>
@@ -81,11 +81,11 @@
81
  </tr>
82
  </tbody>
83
  </table>
84
- </div>
85
 
86
  </div>
87
 
88
- <div class="container pt-5 mt-5 shadow p-5 mb-5 bg-white rounded">
89
  <h2 id="model-overview" style="text-align: center;">Model Overview</h2>
90
  <body>
91
  <p style="text-align: center;">
@@ -98,9 +98,9 @@
98
  VALL-E generates the discrete audio codec codes based on phoneme and acoustic code prompts, corresponding to the target content and the speaker's voice.
99
  VALL-E directly enables various speech synthesis applications, such as zero-shot TTS, speech editing, and content creation combined with other generative AI models like GPT-3.
100
  </p>
101
- </div>
102
 
103
- <div class="container pt-5 mt-5 shadow p-5 mb-5 bg-white rounded">
104
  <h2 id="ljspeech-samples" style="text-align: center;">LJSpeech Samples</h2>
105
  <div class="table-responsive pt-3">
106
  <table class="table table-hover pt-2">
@@ -127,7 +127,7 @@
127
  </tbody>
128
  </table>
129
  </div>
130
- </div>
131
 
132
 
133
  <div class="container pt-5 mt-5 shadow p-5 mb-5 bg-white rounded">
@@ -140,7 +140,9 @@
140
  <th style="text-align: center">Speaker Prompt</th>
141
  <th style="text-align: center">Ground Truth</th>
142
  <th style="text-align: center">VALL-E</th>
143
- <th style="text-align: center">LibriTTS Model</th>
 
 
144
  </tr>
145
  </thead>
146
  <tbody>
@@ -149,6 +151,8 @@
149
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/61-70970-0024/gt.wav" autoplay/>Your browser does not support the audio element.</audio></td>
150
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/61-70970-0024/official.wav" autoplay/>Your browser does not support the audio element.</audio></td>
151
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/61-70970-0024/libritts.wav" autoplay/>Your browser does not support the audio element.</audio></td>
 
 
152
  </tr>
153
  <tr>
154
  <td style="text-align: left;vertical-align:middle;width: 500px">And lay me down in thy cold bed and leave my shining lot.</td>
@@ -156,6 +160,8 @@
156
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/908-157963-0027/gt.wav" autoplay/>Your browser does not support the audio element.</audio></td>
157
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/908-157963-0027/official.wav" autoplay/>Your browser does not support the audio element.</audio></td>
158
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/908-157963-0027/libritts.wav" autoplay/>Your browser does not support the audio element.</audio></td>
 
 
159
  </tr>
160
  <tr>
161
  <td style="text-align: left;vertical-align:middle;width: 500px">Number ten, fresh nelly is waiting on you, good night husband.</td>
@@ -163,6 +169,8 @@
163
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1089-134686-0004/gt.wav" autoplay/>Your browser does not support the audio element.</audio></td>
164
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1089-134686-0004/official.wav" autoplay/>Your browser does not support the audio element.</audio></td>
165
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1089-134686-0004/libritts.wav" autoplay/>Your browser does not support the audio element.</audio></td>
 
 
166
  </tr>
167
  <tr>
168
  <td style="text-align: left;vertical-align:middle;width: 500px">Yea, his honourable worship is within, but he hath a godly minister or two with him, and likewise a leech.</td>
@@ -170,6 +178,8 @@
170
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1221-135767-0014/gt.wav" autoplay/>Your browser does not support the audio element.</audio></td>
171
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1221-135767-0014/official.wav" autoplay/>Your browser does not support the audio element.</audio></td>
172
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1221-135767-0014/libritts.wav" autoplay/>Your browser does not support the audio element.</audio></td>
 
 
173
  </tr>
174
  </tbody>
175
  </table>
@@ -177,7 +187,7 @@
177
  </div>
178
 
179
 
180
- <div class="container pt-5 mt-5 shadow p-5 mb-5 bg-white rounded">
181
  <h2 id="Acoustic-Environment-Maintenance" style="text-align: center;">Acoustic Environment Maintenance</h2>
182
 
183
  <p>
@@ -287,7 +297,7 @@
287
  <p>
288
  To avoid abuse, Well-trained models and services will not be provided.
289
  </p>
290
- </div>
291
 
292
  </article>
293
  </main>
 
40
  In addition, we find VALL-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis.
41
  </p>
42
 
43
+ <!-- <br>
44
  official demo page: <a href="https://valle-demo.github.io/">https://valle-demo.github.io</a>
45
  <br>
46
 
 
48
  my implementation: <a href="https://github.com/lifeiteng/vall-e">https://github.com/lifeiteng/vall-e</a>
49
  <br><br>
50
  This page is for showing reproduced results only, I keep the main parts of the official demo.
51
+ <br><br> -->
52
 
53
+ <!-- <h2 id="model-configs" style="text-align: center;">Model Configs</h2>
54
  <div class="table-responsive pt-3">
55
  <table class="table table-hover pt-2">
56
  <thead>
 
81
  </tr>
82
  </tbody>
83
  </table>
84
+ </div> -->
85
 
86
  </div>
87
 
88
+ <!-- <div class="container pt-5 mt-5 shadow p-5 mb-5 bg-white rounded">
89
  <h2 id="model-overview" style="text-align: center;">Model Overview</h2>
90
  <body>
91
  <p style="text-align: center;">
 
98
  VALL-E generates the discrete audio codec codes based on phoneme and acoustic code prompts, corresponding to the target content and the speaker's voice.
99
  VALL-E directly enables various speech synthesis applications, such as zero-shot TTS, speech editing, and content creation combined with other generative AI models like GPT-3.
100
  </p>
101
+ </div> -->
102
 
103
+ <!-- <div class="container pt-5 mt-5 shadow p-5 mb-5 bg-white rounded">
104
  <h2 id="ljspeech-samples" style="text-align: center;">LJSpeech Samples</h2>
105
  <div class="table-responsive pt-3">
106
  <table class="table table-hover pt-2">
 
127
  </tbody>
128
  </table>
129
  </div>
130
+ </div> -->
131
 
132
 
133
  <div class="container pt-5 mt-5 shadow p-5 mb-5 bg-white rounded">
 
140
  <th style="text-align: center">Speaker Prompt</th>
141
  <th style="text-align: center">Ground Truth</th>
142
  <th style="text-align: center">VALL-E</th>
143
+ <th style="text-align: center">LibriTTS feiteng</th>
144
+ <th style="text-align: center">LibirTTS ours</th>
145
+ <th style="text-align: center">LibriTTS-R ours</th>
146
  </tr>
147
  </thead>
148
  <tbody>
 
151
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/61-70970-0024/gt.wav" autoplay/>Your browser does not support the audio element.</audio></td>
152
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/61-70970-0024/official.wav" autoplay/>Your browser does not support the audio element.</audio></td>
153
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/61-70970-0024/libritts.wav" autoplay/>Your browser does not support the audio element.</audio></td>
154
+ <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="demos_35epoch_valid_best_rerun/audios/librispeech/61-70970-0024/libritts_yk.wav" autoplay/>Your browser does not support the audio element.</audio></td>
155
+ <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="demos_libritts_r_best_valid_35epoch/audios/librispeech/61-70970-0024/libritts_yk.wav" autoplay/>Your browser does not support the audio element.</audio></td>
156
  </tr>
157
  <tr>
158
  <td style="text-align: left;vertical-align:middle;width: 500px">And lay me down in thy cold bed and leave my shining lot.</td>
 
160
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/908-157963-0027/gt.wav" autoplay/>Your browser does not support the audio element.</audio></td>
161
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/908-157963-0027/official.wav" autoplay/>Your browser does not support the audio element.</audio></td>
162
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/908-157963-0027/libritts.wav" autoplay/>Your browser does not support the audio element.</audio></td>
163
+ <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="demos_35epoch_valid_best_rerun/audios/librispeech/61-70970-0024/libritts_yk.wav" autoplay/>Your browser does not support the audio element.</audio></td>
164
+ <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="demos_libritts_r_best_valid_35epoch/audios/librispeech/61-70970-0024/libritts_yk.wav" autoplay/>Your browser does not support the audio element.</audio></td>
165
  </tr>
166
  <tr>
167
  <td style="text-align: left;vertical-align:middle;width: 500px">Number ten, fresh nelly is waiting on you, good night husband.</td>
 
169
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1089-134686-0004/gt.wav" autoplay/>Your browser does not support the audio element.</audio></td>
170
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1089-134686-0004/official.wav" autoplay/>Your browser does not support the audio element.</audio></td>
171
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1089-134686-0004/libritts.wav" autoplay/>Your browser does not support the audio element.</audio></td>
172
+ <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="demos_35epoch_valid_best_rerun/audios/librispeech/61-70970-0024/libritts_yk.wav" autoplay/>Your browser does not support the audio element.</audio></td>
173
+ <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="demos_libritts_r_best_valid_35epoch/audios/librispeech/61-70970-0024/libritts_yk.wav" autoplay/>Your browser does not support the audio element.</audio></td>
174
  </tr>
175
  <tr>
176
  <td style="text-align: left;vertical-align:middle;width: 500px">Yea, his honourable worship is within, but he hath a godly minister or two with him, and likewise a leech.</td>
 
178
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1221-135767-0014/gt.wav" autoplay/>Your browser does not support the audio element.</audio></td>
179
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1221-135767-0014/official.wav" autoplay/>Your browser does not support the audio element.</audio></td>
180
  <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="audios/librispeech/1221-135767-0014/libritts.wav" autoplay/>Your browser does not support the audio element.</audio></td>
181
+ <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="demos_35epoch_valid_best_rerun/audios/librispeech/61-70970-0024/libritts_yk.wav" autoplay/>Your browser does not support the audio element.</audio></td>
182
+ <td style="text-align: center"><audio controls="controls" style="width: 140px;"><source src="demos_libritts_r_best_valid_35epoch/audios/librispeech/61-70970-0024/libritts_yk.wav" autoplay/>Your browser does not support the audio element.</audio></td>
183
  </tr>
184
  </tbody>
185
  </table>
 
187
  </div>
188
 
189
 
190
+ <!-- <div class="container pt-5 mt-5 shadow p-5 mb-5 bg-white rounded">
191
  <h2 id="Acoustic-Environment-Maintenance" style="text-align: center;">Acoustic Environment Maintenance</h2>
192
 
193
  <p>
 
297
  <p>
298
  To avoid abuse, Well-trained models and services will not be provided.
299
  </p>
300
+ </div> -->
301
 
302
  </article>
303
  </main>