Generate tflite model from fine-tuned whisper model

[samuelashraff]

Hi,

Not sure if this is the right place to put this question...

I'm new to Tensorflow and wanted to inquire whether it is possible to convert a fine-tuned Whisper model into .tflite format?

Looking at this Jupyter notebook you guys published, could I just swap the following line:

ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")

with the dataset name pointing to my fine-tuned Whisper model in Hugging face, e.g.:

ds = load_dataset("<my_hugging_face_fine_tuned_model>, "clean", split="validation")

or are there other steps I need to take as well?

I haven't done the fine-tuning yet, but was wondering if it would be compatible with Tensorflow before I start.

Thanks in advance.