Speech, vision & media
ESPnet
Kaldi-style reproducible recipes across a wide range of end-to-end speech tasks.
Overview
Research summary
ESPnet is a PyTorch-based speech processing toolkit organized around reproducible experiment recipes. It covers recognition, text-to-speech, translation, enhancement, diarization, spoken language understanding and singing voice synthesis. Recipes coordinate data preparation, training, inference and evaluation using conventions familiar from Kaldi workflows, while pretrained models and notebooks provide starting points for application development.
Developers can adapt an existing recipe to a dataset or use exported inference components in other systems. The project focuses on a shared experimental and implementation foundation across speech tasks. Its code is Apache-2.0; individual datasets and model artifacts require their own checks.
Repository summary
- Stars
- 9,976
- Open issues
- Unavailable
- Last push
- 2026-09-30
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Version
- Unavailable
Recorded catalogue figures. View repository data and provenance →
Classification
Pricing & services
Paid services unknown
Whether the provider offers paid products or services has not been established.
Licence scope
Implementation
Recorded implementation details and interfaces for ESPnet.
Implementation details
Python and shell experiment workflows built on PyTorch
- Languages
- Python
- Repository type
- source
Recorded interfaces and capabilities
Licence scope
Repository
Repository snapshots, release information and recorded maintenance signals.
Repository snapshot
- Stars
- 9,976
- Open issues
- Unavailable
- Last push
- 2026-09-30
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Archived
- Not recorded
Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).
Maintenance and provenance
- Catalogue snapshot
- 2026-10-06
- Stars source
- Recorded fallback
- Last push source
- Recorded fallback
Documentation
Recorded references and research provenance for this entry.
Recorded sources 4
- https://espnet.github.io/espnet/ Project page · Documentation
- https://github.com/espnet/espnet Linked repository · Research reference
- https://github.com/espnet/espnet/blob/master/README.md Research reference
- https://github.com/espnet/espnet/blob/master/LICENSE Research reference
Research metadata
- Research date
- 2026-10-02
- Catalogue snapshot
- 2026-10-06