Espresso: A fast end-to-end neural speech recognition toolkit. 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)
Keywords for this software
References in zbMATH (referenced in 3 articles )
Showing results 1 to 3 of 3.
- Mirco Ravanelli; Titouan Parcollet; et al: SpeechBrain: A General-Purpose Speech Toolkit (2021) arXiv
- Piotr Żelasko, Daniel Povey, Jan ”Yenda” Trmal, Sanjeev Khudanpur: Lhotse: a speech data representation library for the modern deep learning ecosystem (2021) arXiv
- Yang, Y.-Y., Hira, M., Ni, Z., Chourdia, A., Astafurov, A., Chen, C., Yeh, C.-F., Puhrsch, C., Pollack, D., Genzel, D., Greenberg, D., Yang, E. Z., Lian, J., Mahadeokar, J., Hwang, J., Chen, J., Goldsborough, P., Roy, P., Narenthiran, S., Watanabe, S., Chintala, S., Quenneville-Bélair, V, Shi, Y.: TorchAudio: Building Blocks for Audio and Speech Processing (2021) arXiv