Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion .github/workflows/linux.yml
Original file line number Diff line number Diff line change
Expand Up @@ -475,7 +475,8 @@ jobs:
matrix:
test:
- name: 'Whisper'
cmd: 'tests/python_tests/test_whisper_pipeline.py tests/python_tests/test_whisper_pipeline_static.py'
# TODO: skip some tests temporary untill https://github.com/huggingface/datasets/issues/7647 dataset is fixed
cmd: 'tests/python_tests/test_whisper_pipeline.py tests/python_tests/test_whisper_pipeline_static.py -k "not test_smoke[sample_from_dataset0 and not test_whisper_constructors[sample_from_dataset0 and not test_max_new_tokens[sample_from_dataset0 and not test_language_mode[language and not test_task_mode[sample_from_dataset0 and not test_language_autodetect[sample_from_dataset0 and not test_whisper_config_constructor and not test_language_autodetect[sample_from_dataset1 and not test_language_autodetect[sample_from_dataset2 and not test_initial_prompt_hotwords[sample_from_dataset0 and not test_random_sampling[sample_from_dataset0"'
run_condition: ${{ fromJSON(needs.smart_ci.outputs.affected_components).whisper.test }}
timeout: 45
- name: 'Cacheopt E2E'
Expand Down
3 changes: 2 additions & 1 deletion .github/workflows/mac.yml
Original file line number Diff line number Diff line change
Expand Up @@ -423,7 +423,8 @@ jobs:
matrix:
test:
- name: 'Whisper'
cmd: 'tests/python_tests/test_whisper_pipeline.py'
# TODO: skip some tests temporary untill https://github.com/huggingface/datasets/issues/7647 dataset is fixed
cmd: 'tests/python_tests/test_whisper_pipeline.py -k "not test_smoke[sample_from_dataset0 and not test_whisper_constructors[sample_from_dataset0 and not test_max_new_tokens[sample_from_dataset0 and not test_language_mode[language and not test_task_mode[sample_from_dataset0 and not test_language_autodetect[sample_from_dataset0 and not test_whisper_config_constructor and not test_language_autodetect[sample_from_dataset1 and not test_language_autodetect[sample_from_dataset2 and not test_initial_prompt_hotwords[sample_from_dataset0 and not test_random_sampling[sample_from_dataset0"'
run_condition: ${{ fromJSON(needs.smart_ci.outputs.affected_components).whisper.test }}
timeout: 45
- name: 'Cacheopt E2E'
Expand Down
3 changes: 2 additions & 1 deletion .github/workflows/windows.yml
Original file line number Diff line number Diff line change
Expand Up @@ -534,7 +534,8 @@ jobs:
matrix:
test:
- name: 'Whisper'
cmd: 'tests/python_tests/test_whisper_pipeline.py tests/python_tests/test_whisper_pipeline_static.py'
# TODO: skip some tests temporary untill https://github.com/huggingface/datasets/issues/7647 dataset is fixed
cmd: 'tests/python_tests/test_whisper_pipeline.py tests/python_tests/test_whisper_pipeline_static.py -k "not test_smoke[sample_from_dataset0 and not test_whisper_constructors[sample_from_dataset0 and not test_max_new_tokens[sample_from_dataset0 and not test_language_mode[language and not test_task_mode[sample_from_dataset0 and not test_language_autodetect[sample_from_dataset0 and not test_whisper_config_constructor and not test_language_autodetect[sample_from_dataset1 and not test_language_autodetect[sample_from_dataset2 and not test_initial_prompt_hotwords[sample_from_dataset0 and not test_random_sampling[sample_from_dataset0"'
run_condition: ${{ fromJSON(needs.smart_ci.outputs.affected_components).whisper.test }}
timeout: 45
- name: 'Cacheopt E2E'
Expand Down
6 changes: 4 additions & 2 deletions tests/python_tests/test_whisper_pipeline.py
Original file line number Diff line number Diff line change
Expand Up @@ -179,7 +179,10 @@ def run_genai(

@functools.lru_cache(16)
def get_whisper_dataset(language: str, long_form: bool) -> list:
if not long_form:
# TODO: temporary always use long_form for until "mozilla-foundation/common_voice_11_0"
# https://github.com/huggingface/datasets/issues/7647 dataset is fixed for streaming mode
# if not long_form:
if False:
ds = datasets.load_dataset(
"mozilla-foundation/common_voice_11_0",
language,
Expand All @@ -194,7 +197,6 @@ def get_whisper_dataset(language: str, long_form: bool) -> list:
streaming=True,
trust_remote_code=True,
)

ds = typing.cast(datasets.IterableDataset, ds)
ds = ds.cast_column("audio", datasets.Audio(sampling_rate=16000))
ds = ds.take(MAX_DATASET_LENGTH)
Expand Down