openai/whisper-large-v2 can't run

[LIANGQI0811]

System Info

tt = pipeline(model="openai/whisper-large-v2")
tt("https://hf-mirror.com/datasets/Narsil/asr_dummy/resolve/main/mlk.flac")

print error message like this:

Traceback (most recent call last):
File "", line 1, in
File "/home/developer/.local/lib/python3.10/site-packages/transformers/pipelines/automatic_speech_recognition.py", line 266, in call
return super().call(inputs, **kwargs)
File "/home/developer/.local/lib/python3.10/site-packages/transformers/pipelines/base.py", line 1266, in call
return next(
File "/home/developer/.local/lib/python3.10/site-packages/transformers/pipelines/pt_utils.py", line 126, in next
item = next(self.iterator)
File "/home/developer/.local/lib/python3.10/site-packages/transformers/pipelines/pt_utils.py", line 271, in next
processed = self.infer(next(self.iterator), **self.params)
File "/home/developer/.local/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 741, in next
data = self._next_data()
File "/home/developer/.local/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 801, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "/home/developer/.local/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 35, in fetch
data.append(next(self.dataset_iter))
File "/home/developer/.local/lib/python3.10/site-packages/transformers/pipelines/pt_utils.py", line 188, in next
processed = next(self.subiterator)
File "/home/developer/.local/lib/python3.10/site-packages/transformers/pipelines/automatic_speech_recognition.py", line 486, in preprocess
extra["num_frames"] = processed.pop("num_frames")
File "/usr/lib/python3.10/_collections_abc.py", line 962, in pop
value = self[key]
File "/home/developer/.local/lib/python3.10/site-packages/transformers/feature_extraction_utils.py", line 90, in getitem
return self.data[item]
KeyError: 'num_frames'

Who can help?

No response

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

tt = pipeline(model="openai/whisper-large-v2")
tt("https://hf-mirror.com/datasets/Narsil/asr_dummy/resolve/main/mlk.flac")

Expected behavior

will run and result data

[gSulpizio]

KeyError: 'num_frames' an issue that occurred in older versions. The pipeline expects the feature extractor to return a num_frames key, but it is not being generated or passed correctly in your version. pip install --upgrade transformers accelerator librosa should fix it.