# Bundled data — sources and licenses

This repository bundles audio so the recipe is self-contained. Each dataset is
redistributed under its original license, reproduced/attributed below. Because
**ESC-50 is CC BY-NC**, the bundled artifact as a whole is for
**non-commercial / academic** use.

## Clean speech — LibriTTS (`data/clean/`)

- Subset of LibriTTS: `train-clean-100` (training), `dev-clean` (dev),
  `test-clean` (test). Each `*.wav` ships with its `*.normalized.txt` transcript.
- Source: https://www.openslr.org/60/
- License: **CC BY 4.0**.
- Citation:
  > H. Zen, V. Dang, R. Clark, Y. Zhang, R. J. Weiss, Y. Jia, Z. Chen, Y. Wu.
  > "LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech," Interspeech 2019.

## Noise — ESC-50 (`data/noise/`)

- Full ESC-50 (2000 clips, 5 folds). Folds 1–3 used for training noise, fold 4
  for dev, fold 5 for test (disjoint). `meta/esc50.csv` retained.
- Source: https://github.com/karolpiczak/ESC-50
- License: **CC BY-NC 3.0** (non-commercial).
- Citation:
  > K. J. Piczak. "ESC: Dataset for Environmental Sound Classification,"
  > ACM Multimedia 2015.

## ASR model — Whisper (not bundled)

- `openai/whisper-base.en` is downloaded from the Hugging Face Hub at runtime
  (not redistributed here). License: MIT (OpenAI Whisper).

## Code

- The source code in `ds4se/` and `scripts/` is MIT-licensed — see `LICENSE`.