SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused particularly on speech processing tasks such as speech recognition, speech enhancement, speaker recognition, text-to-speech, and much more. It promotes transparency and replicability by releasing both the pre-trained models and the complete "recipes" of code and algorithms required for training them. This paper presents SpeechBrain 1.0, a significant milestone in the evolution of the toolkit, which now has over 200 recipes for speech, audio, and language processing tasks, and more than 100 models available on Hugging Face. SpeechBrain 1.0 introduces new technologies to support diverse learning modalities, Large Language Model (LLM) integration, and advanced decoding strategies, along with novel models, tasks, and modalities. It also includes a new benchmark repository, offering researchers a unified platform for evaluating models across diverse tasks.
Open-Source Conversational AI with SpeechBrain 1.0 / Ravanelli, Mirco; Parcollet, Titouan; Moumen, Adel; de Langen, Sylvain; Subakan, Cem; Plantinga, Peter; Wang, Yingzhi; Mousavi, Pooneh; Della Libera, Luca; Ploujnikov, Artem; Paissan, Francesco; Borra, Davide; Zaiem, Salah; Zhao, Zeyu; Zhang, Shucong; Karakasidis, Georgios; Yeh, Sung-Lin; Champion, Pierre; Rouhe, Aku; Braun, Rudolf; Mai, Florian; Zuluaga-Gomez, Juan; Mousavi, Seyed Mahed; Nautsch, Andreas; Nguyen, Ha; Liu, Xuechen; Sagar, Sangeet; Duret, Jarod; Mdhaffar, Salima; Laperriere, Gaelle; Rouvier, Mickael; De Mori, Renato; Esteve, Yannick. - In: JOURNAL OF MACHINE LEARNING RESEARCH. - ISSN 1533-7928. - 25:(2024).
Open-Source Conversational AI with SpeechBrain 1.0
Mirco Ravanelli;Seyed Mahed Mousavi;
2024-01-01
Abstract
SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused particularly on speech processing tasks such as speech recognition, speech enhancement, speaker recognition, text-to-speech, and much more. It promotes transparency and replicability by releasing both the pre-trained models and the complete "recipes" of code and algorithms required for training them. This paper presents SpeechBrain 1.0, a significant milestone in the evolution of the toolkit, which now has over 200 recipes for speech, audio, and language processing tasks, and more than 100 models available on Hugging Face. SpeechBrain 1.0 introduces new technologies to support diverse learning modalities, Large Language Model (LLM) integration, and advanced decoding strategies, along with novel models, tasks, and modalities. It also includes a new benchmark repository, offering researchers a unified platform for evaluating models across diverse tasks.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
