doc: update README with 2.0 highlights

This commit is contained in:
Hervé Bredin committed 2021-01-15 13:19:10 +01:00
1 parent 10f8932e89
commit 8696421140
1 file changed
+9 -2
+9 -2
View File
@@ -1,6 +1,13 @@
# Rewriting pyannote.audio from scratch
# Neural speaker diarization with pyannote.audio
This is alpha release of upcoming `pyannote.audio` 2.0 for which it has been decided to rewrite almost everything from scratch to benefit from `pytorch-lightning` framework.
This is the development branch of upcoming `pyannote.audio` 2.0 for which it has been decided to rewrite almost everything from scratch. Highlights of this upcoming release will be:
- a much smaller and cleaner codebase
- Python-first API (the *good old* pyannote-audio CLI will still be available, though)
- multi-GPU and TPU training thanks to [pytorch-lightning](https://pytorchlightning.ai/)
- data augmentation with [torch-audiomentations](https://github.com/asteroid-team/torch-audiomentations)
- [huggingface](https://huggingface.co) model hosting
- [prodigy](https://prodi.gy) recipes for audio annotations
## Installation