Beam search on CoreML will require some model changes to work according to the reference implementation. This is mainly due to CoreML static shapes requiring a new model for each possible beam_size. We have some plans to deal with this so will keep this issue here for tracking purposes.
Beam search on CoreML will require some model changes to work according to the reference implementation. This is mainly due to CoreML static shapes requiring a new model for each possible
beam_size. We have some plans to deal with this so will keep this issue here for tracking purposes.References
Openai implementation: https://github.com/openai/whisper/blob/ba3f3cd54b0e5b8ce1ab3de13e32122d0d5f98ab/whisper/decoding.py#L301-L404