example inference does not work

#1
by eschmidbauer - opened

image.png

>>>
>>> from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
>>>
>>> processor = AutoProcessor.from_pretrained("Intel/whisper-base-onnx-int4")
model = AutoModelForSpeechSeq2Seq.from_pretrained("Intel/whisper-base-onnx-int4")
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
>>> model = AutoModelForSpeechSeq2Seq.from_pretrained("Intel/whisper-base-onnx-int4")
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "python3.11/site-packages/transformers/models/auto/auto_factory.py", line 565, in from_pretrained
    return model_class.from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "python3.11/site-packages/transformers/modeling_utils.py", line 2972, in from_pretrained
    raise EnvironmentError(
OSError: Intel/whisper-base-onnx-int4 does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.

Hi @eschmidbauer , that's because transformers's API doesn't support onnx model inference yet.

Hello, I'm pretty new to this kind of stuff, What could we use to run an inference in that case?

Sign up or log in to comment