You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
🎉 SpeechBrain 1.0 is out. <a href="https://colab.research.google.com/drive/1IEPfKRuvJRSjoxu22GZhb3czfVHsAy0s?usp=sharing"><strong> Check out what's new!</strong></a>
</div>
<!--================Work Area =================-->
<section class="work_area p_120">
<div class="container">
<div class="main_title">
<h2>Key Features</h2>
<p>Open, simple, flexible, well-documented, and with competitive performance.</p>
</div>
<div class="work_inner row">
<div class="col-lg-4">
<div class="work_item">
<i class="lnr lnr-mic"></i>
<a href="#"><h4>Speech</h4></a>
<p>SpeechBrain supports state-of-the-art technologies for speech recognition, enhancement, separation, text-to-speech, speaker recognition, speech-to-speech translation, spoken language understanding, and beyond.</p>
</div>
</div>
<div class="col-lg-4">
<div class="work_item">
<i class="lnr lnr-volume"></i>
<a href="#"><h4>Audio</h4></a>
<p>SpeechBrain encompasses a wide range of audio technologies, including vocoding, audio augmentation, feature extraction, sound event detection, beamforming, and other multi-microphone signal processing capabilities.</p>
</div>
</div>
<div class="col-lg-4">
<div class="work_item">
<i class="lnr lnr-book"></i>
<a href="#"><h4>Text</h4></a>
<p>SpeechBrain offers user-friendly tools for training Language Models, supporting technologies ranging from basic n-gram LMs to modern Large Language Models. Our platform seamlessly integrates them into speech processing pipelines and facilitates the creation of customizable chatbots.</p>
</div>
</div>
<div class="col-lg-4">
<div class="work_item">
<i class="lnr lnr-rocket"></i>
<a href="#"><h4>Technology</h4></a>
<p>SpeechBrain leverages the most advanced deep learning technologies, including methods for self-supervised learning, continual learning, diffusion models, Bayesian deep learning, and interpretable neural networks.</p>
</div>
</div>
<div class="col-lg-4" style="margin:0 auto">
<div class="work_item">
<i class="lnr lnr-magic-wand"></i>
<a href="#"><h4>Research & Development</h4></a>
<p>SpeechBrain is engineered to accelerate the research and development of Conversational AI technologies. It comes with pre-built recipes for popular datasets. Extensive documentation and tutorials are available to support newcomers.</p>
</div>
</div>
<div class="col-lg-4" style="margin:0 auto">
<div class="work_item">
<i><img src="img/hf.svg" style="width:60px"/></i>
<a href="#"><h4>HuggingFace!</h4></a>
<p>SpeechBrain offers pre-trained models with user-friendly interfaces, making tasks like transcription, speaker verification, speech enhancement, and source separation easier than ever.</p>
</div>
</div>
</div>
</div>
</section>
<!--================End Work Area =================-->
<!--================BIG MENU Area =================-->
<a class="nav-link" id="profile-tab" data-toggle="tab" href="#profile" role="tab" aria-controls="profile" aria-selected="false">Easy to use</a>
</li>
<li class="nav-item">
<a class="nav-link" id="contact-tab" data-toggle="tab" href="#contact" role="tab" aria-controls="contact" aria-selected="false">Easy to customize</a>
</li>
</ul>
<div class="tab-content" id="myTabContent">
<div class="tab-pane fade show active" id="home" role="tabpanel" aria-labelledby="home-tab">
<div class="row made_life_text">
<div class="col-lg-6">
<div class="left_side_text">
<h3>Adapts to your needs.</h3>
<h6>You can install SpeechBrain via PyPI for quick access to its functionalities, or through a local install for accessing recipes and delving deeper into the toolkit.</h6>
<a class="main_btn" href="https://speechbrain.readthedocs.io/">Get Started Now</a>
SpeechBrain is designed for research and development. Hence, flexibility, transparency, and replicability are core concepts to enhance our daily workflows. Users can easily define custom deep learning models, losses, training/evaluation loops, and input pipelines/transformations, and easily integrate into existing pipelines.
</h6>
<a class="main_btn" href="https://speechbrain.readthedocs.io/">Get Started Now</a>
</div>
</div>
<div class="col-lg-6">
<div class="chart_img">
<pre><code class="python">
class ASR_Brain(sb.Brain):
def compute_forward(self, batch, stage):
# Compute features (mfcc, fbanks, etc.) on the fly
features = self.hparams.compute_features(batch.wavs)
# Improve robustness with pre-built augmentations
features = self.hparams.augment(features)
# Apply your custom model
return self.modules.myCustomModel(features)
</code></pre>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</section>
<!--================END BIG MENU Area =================-->
<!--================Screen Area =================-->
<section class="screen_area text-center p_120">
<div class="container">
<div class="main_title">
<h2>Sponsors</h2>
<p> <a href="https://drive.google.com/file/d/1G1T2kbqMA1Rluzax5PcGa7TFV--mmKvX/view?usp=sharing"> Our new call for sponsors (2024) is now open. </a></p>