Repository files navigation

| 📘Tutorials | 🌐Website | 📚Documentation | 🤝Contributing | 🤗HuggingFace |▶️YouTube | 🐦X |

Please, help our community project. Star on GitHub!

Exciting News (January, 2024): Discover what is new in SpeechBrain 1.0here!

• SpeechBrain is anopen-sourcePyTorch toolkit that acceleratesConversational AI development, i.e., the technology behindspeech assistants,chatbots, andlarge language models.

• It is crafted for fast and easy creation of advanced technologies forSpeech andText Processing.

• With the rise ofdeep learning, once-distant domains like speech processing and NLP are now very close. A well-designed neural network and large datasets are all you need.

• We think it is now time for aholistic toolkit that, mimicking the human brain, jointly supports diverse technologies for complex Conversational AI systems.

• This spansspeech recognition,speaker recognition,speech enhancement,speech separation,language modeling,dialogue, and beyond.

• Aligned with our long-term goal of natural human-machine conversation, including for non-verbal individuals, we have recently added support for theEEG modality.

• We share over 200 competitive trainingrecipes on more than 40 datasets supporting 20 speech and text processing tasks (see below).

• We support both training from scratch and fine-tuning pretrained models such asWhisper,Wav2Vec2,WavLM,Hubert,GPT2,Llama2, and beyond. The models onHuggingFace can be easily plugged in and fine-tuned.

• For any task, you train the model using these commands:

pythontrain.pyhparams/train.yaml

• The hyperparameters are encapsulated in a YAML file, while the training process is orchestrated through a Python script.

• We maintained a consistent code structure across different tasks.

• For better replicability, training logs and checkpoints are hosted on Dropbox.

• Access over 100 pretrained models hosted onHuggingFace.
• Each model comes with a user-friendly interface for seamless inference. For example, transcribing speech using a pretrained model requires just three lines of code:

fromspeechbrain.inferenceimportEncoderDecoderASRasr_model=EncoderDecoderASR.from_hparams(source="speechbrain/asr-conformer-transformerlm-librispeech",savedir="pretrained_models/asr-transformer-transformerlm-librispeech")asr_model.transcribe_file("speechbrain/asr-conformer-transformerlm-librispeech/example.wav")

• We are deeply dedicated to promoting inclusivity and education.
• We have authored over 30tutorials that not only describe how SpeechBrain works but also help users familiarize themselves with Conversational AI.
• Every class or function has clear explanations and examples that you can run. Check out thedocumentation for more details 📚.

• 🚀Research Acceleration: Speeding up academic and industrial research. You can develop and integrate new models effortlessly, comparing their performance against our baselines.

• ⚡️Rapid Prototyping: Ideal for quick prototyping in time-sensitive projects.

• 🎓Educational Tool: SpeechBrain's simplicity makes it a valuable educational resource. It is used by institutions likeMila,Concordia University,Avignon University, and many others for student training.

To get started with SpeechBrain, follow these simple steps:

1. Install SpeechBrain using PyPI:

   pip install speechbrain

2. Access SpeechBrain in your Python code:

   importspeechbrainassb

This installation is recommended for users who wish to conduct experiments and customize the toolkit according to their needs.

1. Clone the GitHub repository and install the requirements:

   git clone https://github.com/speechbrain/speechbrain.gitcd speechbrainpip install -r requirements.txtpip install --editable.

2. Access SpeechBrain in your Python code:

   importspeechbrainassb

Any modifications made to thespeechbrain package will be automatically reflected, thanks to the--editable flag.

Ensure your installation is correct by running the following commands:

pytest testspytest --doctest-modules speechbrain

In SpeechBrain, you can train a model for any task using the following steps:

cdrecipes/<dataset>/<task>/pythonexperiment.pyparams.yaml

The results will be saved in theoutput_folder specified in the YAML file.

• Website: Explore general information on theofficial website.

• Tutorials: Start withbasic tutorials covering fundamental functionalities. Find advanced tutorials and topics in the Tutorial notebooks category in theSpeechBrain documentation.

• Documentation: Detailed information on the SpeechBrain API, contribution guidelines, and code is available in thedocumentation.

• SpeechBrain is a versatile framework designed for implementing a wide range of technologies within the field of Conversational AI.
• It excels not only in individual task implementations but also in combining various technologies into complex pipelines.

SpeechBrain includes a range of native functionalities that enhance the development of Conversational AI technologies. Here are some examples:

• Training Orchestration: TheBrain class serves as a fully customizable tool for managing training and evaluation loops over data. It simplifies training loops while providing the flexibility to override any part of the process.

• Hyperparameter Management: A YAML-based hyperparameter file specifies all hyperparameters, from individual numbers (e.g., learning rate) to complete objects (e.g., custom models). This elegant solution drastically simplifies the training script.

• Dynamic Dataloader: Enables flexible and efficient data reading.

• GPU Training: Supports single and multi-GPU training, including distributed training.

• Dynamic Batching: On-the-fly dynamic batching enhances the efficient processing of variable-length signals.

• Mixed-Precision Training: Accelerates training through mixed-precision techniques.

• Efficient Data Reading: Reads large datasets efficiently from a shared Network File System (NFS) viaWebDataset.

• Hugging Face Integration: Interfaces seamlessly withHuggingFace for popular models such as wav2vec2 and Hubert.

• Orion Integration: Interfaces withOrion for hyperparameter tuning.

• Speech Augmentation Techniques: Includes SpecAugment, Noise, Reverberation, and more.

• Data Preparation Scripts: Includes scripts for preparing data for supported datasets.

SpeechBrain is rapidly evolving, with ongoing efforts to support a growing array of technologies in the future.

• SpeechBrain integrates a variety of technologies, including those that achieves competitive or state-of-the-art performance.

• For a comprehensive overview of the achieved performance across different tasks, datasets, and technologies, please visithere.

• SpeechBrain is released under theApache License, version 2.0, a popular BSD-like license.
• You are free to redistribute SpeechBrain for both free and commercial purposes, with the condition of retaining license headers. Unlike the GPL, the Apache License is not viral, meaning you are not obligated to release modifications to the source code.

We have ambitious plans for the future, with a focus on the following priorities:

• Scale Up: We aim to provide comprehensive recipes and technologies for training massive models on extensive datasets.

• Scale Down: While scaling up delivers unprecedented performance, we recognize the challenges of deploying large models in production scenarios. We are focusing on real-time, streamable, and small-footprint Conversational AI.

• Multimodal Large Language Models: We envision a future where a single foundation model can handle a wide range of text, speech, and audio tasks. Our core team is focused on enabling the training of advanced multimodal LLMs.

• SpeechBrain is a community-driven project, led by a core team with the support of numerous international collaborators.
• We welcome contributions and ideas from the community. For more information, checkhere.

• SpeechBrain is an academically driven project and relies on the passion and enthusiasm of its contributors.
• As we cannot rely on the resources of a large company, we deeply appreciate any form of support, including donations or collaboration with the core team.
• If you're interested in sponsoring SpeechBrain, please reach out to us atspeechbrainproject@gmail.com.
• A heartfelt thank you to all our sponsors, including the current ones:

If you use SpeechBrain in your research or business, please cite it using the following BibTeX entry:

@article{speechbrain_v1,author  ={Mirco Ravanelli and Titouan Parcollet and Adel Moumen and Sylvain de Langen and Cem Subakan and Peter Plantinga and Yingzhi Wang and Pooneh Mousavi and Luca Della Libera and Artem Ploujnikov and Francesco Paissan and Davide Borra and Salah Zaiem and Zeyu Zhao and Shucong Zhang and Georgios Karakasidis and Sung-Lin Yeh and Pierre Champion and Aku Rouhe and Rudolf Braun and Florian Mai and Juan Zuluaga-Gomez and Seyed Mahed Mousavi and Andreas Nautsch and Ha Nguyen and Xuechen Liu and Sangeet Sagar and Jarod Duret and Salima Mdhaffar and Ga{{\"e}}lle Laperri{{\`e}}re and Mickael Rouvier and Renato De Mori and Yannick Est{{\`e}}ve},title   ={Open-Source Conversational AI with SpeechBrain 1.0},journal ={Journal of Machine Learning Research},year    ={2024},volume  ={25},number  ={333},url     ={http://jmlr.org/papers/v25/24-0991.html}}@misc{speechbrain,title={{SpeechBrain}: A General-Purpose Speech Toolkit},author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},year={2021},eprint={2106.04624},archivePrefix={arXiv},primaryClass={eess.AS},note={arXiv:2106.04624}}