SpeechBrain is a toolkit for developing and evaluating speech-processing and conversational AI systems. It brings together neural-network components, pretrained models and reproducible training recipes for tasks including automatic speech recognition, speaker recognition, speech enhancement and speech separation.
The toolkit is designed to let researchers combine neural architectures and training techniques without having to implement every part of a speech-processing system from scratch. Its modular components can be used to construct acoustic models, extract representations from speech, apply augmentation and evaluate predictions. SpeechBrain also provides interfaces for accessing pretrained models, allowing users to perform inference or adapt existing models to new datasets. The same framework supports both conventional acoustic modelling experiments and applications that combine speech with language understanding, making it useful for research involving several related audio and text tasks.
This is free and open source software.
Key Features
- Automatic speech recognition – supports CTC, attention-based encoder-decoder and transducer architectures.
- Speaker recognition – provides models and recipes for speaker identification, verification and embedding extraction.
- Speech enhancement – includes approaches for reducing background noise and improving speech intelligibility.
- Speech separation – separates overlapping speakers and other mixed audio signals.
- Speech synthesis – provides facilities for text-to-speech research and waveform generation.
- Language identification – supports classification of spoken languages from audio recordings.
- Speech representations – integrates pretrained models including wav2vec and HuBERT through Hugging Face interfaces.
- Neural architectures – includes recurrent networks, convolutional networks, Transformers, Conformers and customizable encoder-decoder components.
- Data augmentation – provides SpecAugment, noise addition, reverberation and other transformations for training.
- Language modelling – supports recurrent and Transformer-based language models for decoding.
- Pretrained models – offers ready-to-use models for inference and transfer learning through the Hugging Face ecosystem.
- Training recipes – includes dataset preparation, model configuration, training, evaluation and experiment tracking.
- Distributed training – supports GPU computation, mixed precision and training across multiple devices.
- Hyperparameter optimization – integrates tools for tuning training parameters and comparing experiments.
Website: github.com/speechbrain/speechbrain
Support:
Developer: Mirco Ravanelli, Titouan Parcollet and contributors
License: Apache License 2.0
SpeechBrain is written in Python. Learn Python with our recommended free books and free tutorials.
Related Software
| Speech Recognition Tools | |
|---|---|
| Whisper | Automatic speech recognition (system trained on 680,000 hours of data |
| whisper.cpp | Run Whisper locally with fast, efficient C/C++ speech recognition |
| Flashlight | Fast, flexible machine learning library written entirely in C++. |
| sherpa-onnx | Offline speech recognition for many platforms and languages |
| Kaldi | C++ toolkit designed for speech recognition researchers. |
| FunASR | Versatile speech recognition toolkit for real-world audio |
| faster-whisper | Faster Whisper transcription with reduced memory use |
| SpeechBrain | All-in-one conversational AI toolkit based on PyTorch |
| Handy | Offline speech-to-text application |
| ESPnet | End-to-End speech processing toolkit |
| PocketSphinx | Lightweight speech recognition for embedded and mobile use |
| deepspeech.pytorch | Implementation of DeepSpeech2 using Baidu Warp-CTC. |
| Epicenter | Transcription application with global speech-to-text functionality |
| Julius | Two-pass large vocabulary continuous speech recognition engine |
| Speech Note | Write notes, transcribe speech, translate text and read content aloud |
| aTrain | Private local transcription of recorded speech through a polished GUI |
| hyprwhspr | Native speech-to-text designed for Arch / Omarchy |
| Vocalinux | Local voice dictation through a clean desktop interface |
| ostt | Open Speech-to-Text |
| Simon | Flexible speech recognition software |
Read our verdict in the software roundup.
LinuxLinks helps you discover the best free and open source software for Linux. Explore our extensive collection of recommended applications, including alternatives to popular proprietary software.We also publish software reviews, Linux tutorials, hardware reviews, free programming books and articles covering the wider open source community. Browse our Linux resources to discover more. Know a useful free and open source Linux application we haven't covered? Suggest a program for inclusion. Has your software been featured on LinuxLinks? Display one of our Featured on LinuxLinks badges on your website or GitHub README. |


Please read our Comment Policy before commenting.