RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition

Abstract

Modern public ASR tools usually provide rich support for training various sequence-to-sequence (S2S) models, but rather simple support for decoding open-vocabulary scenarios only. For closed-vocabulary scenarios, public tools supporting lexical-constrained decoding are usually only for classical ASR, or do not support all S2S models. To eliminate this restriction on research possibilities such as modeling unit choice, we present RASR2 in this work, a research-oriented generic S2S decoder implemented in C++. It offers a strong flexibility/compatibility for various S2S models, language models, label units/topologies and neural network architectures. It provides efficient decoding for both open- and closed-vocabulary scenarios based on a generalized search framework with rich support for different search modes and settings. We evaluate RASR2 with a wide range of experiments on both switchboard and Librispeech corpora. Our source code is public online.

arXiv commentaccepted at Interspeech 2023

References in corpus (9)

• TensorFlow: A system for large-scale machine learning
• Sequence Transduction with Recurrent Neural Networks
• SpeechBrain: A General-Purpose Speech Toolkit
• Language Modeling with Deep Transformers
• RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition
• Flashlight: Enabling Innovation in Tools for Machine Learning
• Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition
• Robust Beam Search for Encoder-Decoder Attention Based Speech Recognition without Length Bias
• On Language Model Integration for RNN Transducer based Speech Recognition