Extractor refactor, S3 support
Some checks failed
CI / Typos (push) Successful in 1m5s
CI / Clippy (push) Failing after 1m50s
CI / Build and test (push) Successful in 3m1s

This commit is contained in:
2026-03-06 17:49:12 -08:00
parent 77b3125af4
commit aecc84233b
31 changed files with 2676 additions and 675 deletions

View File

@@ -9,8 +9,7 @@ name = "dataset"
# working_dir = ".pile"
# Data sources available in this dataset
source."music" = { type = "flac", path = ["music", "music-2"] }
source."music" = { type = "filesystem", path = "music" }
# This dataset's schema.
# Defines normalized fields that are extracted from source entries on-demand.