github
/
seamless_communication
miroir de https://github.com/facebookresearch/seamless_communication.git


			
				
					
						
						
							12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849
							<!DOCTYPE html>
<html>

<head>
	<meta charset="UTF-8">
	<title>Seamless Communication</title>
	<link rel="stylesheet" type="text/css" href="styles.css">
	<script src="jquery-3.5.js"></script>
</head>

<body>
	<div class="container">
		<h1 id="text1">Seamless Communication Demo</h1>
		<div id="intro">
			<br>
		</div>
	</div>

	<div class="content-container">
		<ul>
			<li>Direct Speech-to-Speech Translation With Discrete Units: [<a href="demo/direct_s2st_units/index.html"
				target="_blank">demo</a>, <a href="https://arxiv.org/abs/2107.05604" target="_blank">paper</a>, <a
				href="https://github.com/pytorch/fairseq/tree/main/examples/speech_to_speech/docs/direct_s2st_discrete_units.md"
				target="_blank">code</a>]</li>
			<!--  -->
			<li>Textless Speech-to-Speech Translation on Real Data: [<a href="demo/textless_s2st_real_data/index.html"
					target="_blank">demo</a>, <a href="https://arxiv.org/abs/2112.08352" target="_blank">paper</a>, <a
					href="https://github.com/pytorch/fairseq/tree/main/examples/speech_to_speech/docs/textless_s2st_real_data.md"
					target="_blank">code</a>]</li>
			<!--  -->
			<li>Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data
				Augmentation: [<a href="demo/enhanced_direct_s2st_units/index.html" target="_blank">demo</a>, <a 
					href="https://arxiv.org/abs/2204.02967" target="_blank">paper</a>, <a
					href="https://github.com/pytorch/fairseq/blob/main/examples/speech_to_speech/docs/enhanced_direct_s2st_discrete_units.md"
					target="_blank">code</a>]
			</li>
			<!--  -->
			<li>A Holistic Cascade System, Benchmark, and Human Evaluation Protocol for Expressive Speech-to-Speech Translation
				[<a href="demo/cascade_expressive_s2st/index.html" target="_blank">demo</a>]
			</li>
			<!--  -->
			<li>Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation: [<a href="demo/dino_pretssel/index.html" target="_blank">demo</a>]</li>
		</ul>
	</div>

	<link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.3.0/css/font-awesome.min.css">
</body>

</html>