Skip to content

Commit

Permalink
result
Browse files Browse the repository at this point in the history
  • Loading branch information
@LauraGPT
LauraGPT committed Sep 30, 2023
1 parent 715d263 commit 79642ab
Show file tree
Hide file tree
Showing 21 changed files with 189 additions and 31 deletions.
Binary file added audio/tts_samples/p1995_1837_000020_000000/1995_1836_000003_000002_16k.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p1995_1837_000020_000000/lauraGPT_p1995_1837_000020_000000.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p1995_1837_000020_000000/prompt_p1995_1837_000020_000000.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p1995_1837_000020_000000/valle_phn_p1995_1837_000020_000000.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p1995_1837_000020_000000/valle_token_p1995_1837_000020_000000.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p2830_3980_000018_000001/2830_3980_000018_000000_16k.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p2830_3980_000018_000001/lauraGPT_p2830_3980_000018_000001.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p2830_3980_000018_000001/prompt_p2830_3980_000018_000001.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p2830_3980_000018_000001/valle_phn_p2830_3980_000018_000001.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p2830_3980_000018_000001/valle_token_p2830_3980_000018_000001.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p6829_68771_000046_000000/6829_68769_000030_000000_16k.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p6829_68771_000046_000000/lauraGPT_p6829_68771_000046_000000.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p6829_68771_000046_000000/prompt_p6829_68771_000046_000000.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p6829_68771_000046_000000/valle_phn_p6829_68771_000046_000000.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p6829_68771_000046_000000/valle_token_p6829_68771_000046_000000.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p8230_279154_000004_000008/8230_279154_000019_000000_16k.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p8230_279154_000004_000008/lauraGPT_p8230_279154_000004_000008.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p8230_279154_000004_000008/prompt_p8230_279154_000004_000008.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p8230_279154_000004_000008/valle_phn_p8230_279154_000004_000008.wav
View file
Binary file not shown.
Binary file added audio/tts_samples/p8230_279154_000004_000008/valle_token_p8230_279154_000004_000008.wav
View file
Binary file not shown.
220 changes: 189 additions & 31 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -328,39 +328,197 @@ <h4>1. Automatic speech recognition (ASR) samples</h4>
</table>
</div>

<!-- <h4>2. Text-to-speech synthesis (TTS) samples</h4>-->
<!-- <br/>-->
<!-- <div class="table-responsive">-->
<!-- <table class="table table-striped table-bordered">-->
<!-- <thead>-->
<!-- <tr>-->
<!-- <th class="text-center align-middle">Prompt text</th>-->
<!-- <th class="text-center align-middle">Text</th>-->
<!-- <th class="text-center align-middle">Prompt Speech + Synthesis Speech</th>-->
<!-- </tr>-->
<!-- </thead>-->
<!-- <tbody class="text-center align-middle">-->
<!-- <tr>-->
<!-- <td>-->
<!-- later in accordance with what i believe to be the modern practice-->
<!-- </td>-->
<!-- <td>-->
<!-- <p> i always accept the gift, after deprecating the-->
<!-- honour with words and gestures, and a little later,-->
<!-- in accordance with what i believe to be the modern-->
<!-- practice, return the compliment. </p>-->
<!-- </td>-->
<!-- <td>-->
<!-- <audio controls="controls">-->
<!-- <source src="audio/ptts/tts_libritts_2104_78240_000016_000000.wav" type="audio/wav" />-->
<!-- </audio>-->
<!-- </td>-->
<!-- </tr>-->
<h4>2. Text-to-speech synthesis (TTS) samples</h4>
<br/>
<h6>[Prompt: 1995_1837_000020_000000] Up in the sick room Zora lay on the little white bed. [Continuation: 1995_1836_000003_000002] At last the Cotton Combine was to all appearances an assured fact and he was slated for the Senate.</h6>
<div class="table-responsive">
<table class="table table-striped table-bordered">
<thead>
<tr>
<th class="text-center align-middle">Prompt wav (16k)</th>
<th class="text-center align-middle">Ground-truth (16k)</th>
<th class="text-center align-middle">VALLE-Phone</th>
<th class="text-center align-middle">VALLE-Token</th>
<th class="text-center align-middle">LauraGPT</th>
</tr>
</thead>
<tbody class="text-center align-middle">
<tr>
<td>
<audio controls="controls">
<source src="audio/tts_samples/p1995_1837_000020_000000/prompt_p1995_1837_000020_000000.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p1995_1837_000020_000000/1995_1836_000003_000002_16k.wav" type="audio/wav" />
</audio>
</td>

<!-- </tbody>-->
<!-- </table>-->
<!-- </div>-->
<td>
<audio controls="controls">
<source src="audio/tts_samples/p1995_1837_000020_000000/valle_phn_p1995_1837_000020_000000.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p1995_1837_000020_000000/valle_token_p1995_1837_000020_000000.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p1995_1837_000020_000000/lauraGPT_p1995_1837_000020_000000.wav" type="audio/wav" />
</audio>
</td>
</tr>

<!-- <br/>-->
<div class="table-responsive">
<table class="table table-striped table-bordered">
<h6>[Prompt: 2830_3980_000018_000001] Humble man that he was, he will not now take a back seat. [Continuation: 2830_3980_000018_000000] Against these boasting, false apostles, Paul boldly defends his apostolic authority and ministry.</h6>

<thead>
<tr>
<th class="text-center align-middle">Prompt wav (16k)</th>
<th class="text-center align-middle">Ground-truth (16k)</th>
<th class="text-center align-middle">VALLE-Phone</th>
<th class="text-center align-middle">VALLE-Token</th>
<th class="text-center align-middle">LauraGPT</th>
</tr>
</thead>
<tbody class="text-center align-middle">
<tr>
<td>
<audio controls="controls">
<source src="audio/tts_samples/p2830_3980_000018_000001/prompt_p2830_3980_000018_000001.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p2830_3980_000018_000001/2830_3980_000018_000000_16k.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p2830_3980_000018_000001/valle_phn_p2830_3980_000018_000001.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p2830_3980_000018_000001/valle_token_p2830_3980_000018_000001.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p2830_3980_000018_000001/lauraGPT_p2830_3980_000018_000001.wav" type="audio/wav" />
</audio>
</td>
</tr>

<!-- <br/>-->
<div class="table-responsive">
<table class="table table-striped table-bordered">
<h6>[Prompt: 6829_68771_000046_000000] A sudden wave of scarlet swept over Eliza's face. [Continuation: 6829_68769_000030_000000] Then he deliberately locked Kenneth and Beth in with the forger, and retreated along the passage.</h6>

<thead>
<tr>
<th class="text-center align-middle">Prompt wav (16k)</th>
<th class="text-center align-middle">Ground-truth (16k)</th>
<th class="text-center align-middle">VALLE-Phone</th>
<th class="text-center align-middle">VALLE-Token</th>
<th class="text-center align-middle">LauraGPT</th>
</tr>
</thead>
<tbody class="text-center align-middle">
<tr>
<td>
<audio controls="controls">
<source src="audio/tts_samples/p6829_68771_000046_000000/prompt_p6829_68771_000046_000000.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p6829_68771_000046_000000/6829_68769_000030_000000_16k.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p6829_68771_000046_000000/valle_phn_p6829_68771_000046_000000.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p6829_68771_000046_000000/valle_token_p6829_68771_000046_000000.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p6829_68771_000046_000000/lauraGPT_p6829_68771_000046_000000.wav" type="audio/wav" />
</audio>
</td>
</tr>

<!-- <br/>-->
<div class="table-responsive">
<table class="table table-striped table-bordered">
<h6>[Prompt: 8230_279154_000004_000008] To deal with this problem, we must have a theory of memory. [Continuation: 8230_279154_000019_000000] The first of our vague but indubitable data is that there is knowledge of the past.</h6>

<thead>
<tr>
<th class="text-center align-middle">Prompt wav (16k)</th>
<th class="text-center align-middle">Ground-truth (16k)</th>
<th class="text-center align-middle">VALLE-Phone</th>
<th class="text-center align-middle">VALLE-Token</th>
<th class="text-center align-middle">LauraGPT</th>
</tr>
</thead>
<tbody class="text-center align-middle">
<tr>
<td>
<audio controls="controls">
<source src="audio/tts_samples/p6829_68771_000046_000000/lauraGPT_p6829_68771_000046_000000.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p8230_279154_000004_000008/8230_279154_000019_000000_16k.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p8230_279154_000004_000008/valle_phn_p8230_279154_000004_000008.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p8230_279154_000004_000008/valle_token_p8230_279154_000004_000008.wav" type="audio/wav" />
</audio>
</td>

<td>
<audio controls="controls">
<source src="audio/tts_samples/p8230_279154_000004_000008/lauraGPT_p8230_279154_000004_000008.wav" type="audio/wav" />
</audio>
</td>
</tr>

</tbody>
</table>
</div>

<h4>3. Speech to text translation (S2TT) samples</h4>
<br/>
Expand Down

0 comments on commit 79642ab

Please sign in to comment.