Key Features
Open, simple, flexible, well-documented, and with competitive performance.
Speech
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.
Audio
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.
Text
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.
Technology
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.
Research & Development
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.
HuggingFace!
SpeechBrain offers pre-trained models with user-friendly interfaces, making tasks like transcription, speaker verification, speech enhancement, and source separation easier than ever.
Why SpeechBrain?
Adapts to your needs.
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.
Get Started Now
# From PyPI
pip install speechbrain
# Local installation
git clone https://github.com/speechbrain/speechbrain.git
cd speechbrain
pip install -r requirements.txt
pip install --editable .
A single command.
Each SpeechBrain recipe defines all hyperparameters into a single YAML file. The training process is then orchestrated by a Python script.
Get Started Now
cd recipes/{dataset}/{task}/train
# Train the model using the default recipe
python train.py hparams/train.yaml
# Train the model with a hyperparameter tweak
python train.py hparams/train.yaml --learning_rate=0.1
Built for research.
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.
Get Started Now
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)
Previous Sponsors
Collaborators
