freewym/espresso
A modular end-to-end neural speech recognition toolkit built on PyTorch and fairseq.
Not currently ranked — collecting fresh signals.
star history
Espresso is an open-source ASR toolkit providing state-of-the-art training recipes for speech datasets including WSJ, LibriSpeech, and Switchboard. It supports distributed training across GPUs and nodes, and implements various decoding approaches including CTC decoding, Transducer models, and Conformer encoders. The toolkit features on-the-fly feature extraction from raw waveforms and supports word-based language model fusion with a parallelized decoder.
Frequently asked
- What is freewym/espresso?
- A modular end-to-end neural speech recognition toolkit built on PyTorch and fairseq.
- Is espresso open source?
- Yes — freewym/espresso is an open-source project tracked on heatdrop.
- What language is espresso written in?
- freewym/espresso is primarily written in Python.
- How popular is espresso?
- freewym/espresso has 939 stars on GitHub.
- Where can I find espresso?
- freewym/espresso is on GitHub at https://github.com/freewym/espresso.