Espresso: A Fast End-to-end Neural Speech Recognition Toolkit

Abstract

We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit fairseq. Espresso supports distributed training across GPUs and computing nodes, and features various decoding approaches commonly employed in ASR, including look-ahead word-based language model fusion, for which a fast, parallelized decoder is implemented. Espresso achieves state-of-the-art ASR performance on the WSJ, LibriSpeech, and Switchboard data sets among other end-to-end systems without data augmentation, and is 4--11x faster for decoding than similar systems (e.g. ESPnet).

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2019espresso

Related papers

• Espnet: End-to-end Speech Processing Toolkit (2018)22.17
• Espnet-se: End-to-end Speech Enhancement And Separation Toolkit Designed For Asr Integration (2020)13.55
• Espnet-tts: Unified, Reproducible, And Integratable Open Source End-to-end Text-to-speech Toolkit (2019)23.32
• The 2020 Espnet Update: New Features, Broadened Applications, Performance Improvements, And Future Plans (2020)18.20
• EURO: Espnet Unsupervised ASR Open-source Toolkit (2022)6.77
• Speechnet: Weakly Supervised, End-to-end Speech Recognition At Industrial Scale (2022)0.00
• User-friendly Automatic Transcription Of Low-resource Languages: Plugging Espnet Into Elpis (2020)2.26
• Fast Offline Transformer-based End-to-end Automatic Speech Recognition For Real-world Applications (2021)7.16