Skip to content

Commit

Permalink
188 upgrade datasets (#209)
Browse files Browse the repository at this point in the history
* feat: 🎸 upgrade datasets to 2.1.0

* test: 💍 remove test because the dataset does not exist anymore
  • Loading branch information
severo authored Apr 14, 2022
1 parent 4f940cb commit 751053e
Show file tree
Hide file tree
Showing 3 changed files with 7 additions and 18 deletions.
12 changes: 6 additions & 6 deletions poetry.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ apache-beam = "^2.33.0"
appdirs = "^1.4.4"
bs4 = "^0.0.1"
conllu = "^4.4.1"
datasets = { extras = ["audio", "vision"], version = "^2.0.0" }
datasets = { extras = ["audio", "vision"], version = "^2.1.0" }
diskcache = "^5.2.1"
function-parser = "^0.0.3"
gdown = "^4.2.0"
Expand Down
11 changes: 0 additions & 11 deletions tests/models/test_row.py
Original file line number Diff line number Diff line change
Expand Up @@ -63,14 +63,3 @@ def test_audio_dataset() -> None:
rows = get_rows("abidlabs/test-audio-1", "test", "train", rows_max_number=ROWS_MAX_NUMBER)
assert len(rows) == 1
assert rows[0]["Output"]["sampling_rate"] == 48000


def test_libsndfile() -> None:
# see https://github.com/huggingface/datasets-preview-backend/issues/194
rows = get_rows("polinaeterna/ml_spoken_words", "ar_opus", "train", rows_max_number=ROWS_MAX_NUMBER)
assert len(rows) == ROWS_MAX_NUMBER
assert rows[0]["audio"]["sampling_rate"] == 48000

rows = get_rows("polinaeterna/ml_spoken_words", "ar_wav", "train", rows_max_number=ROWS_MAX_NUMBER)
assert len(rows) == ROWS_MAX_NUMBER
assert rows[0]["audio"]["sampling_rate"] == 16000

0 comments on commit 751053e

Please sign in to comment.