whisper-large-v3-turbo-gguf.ipynb doesn't work

#1
by alejsch84 - opened

When trying to load the model (either using pipeline or AutoModelForSpeechSeq2Seq.from_pretrained) the following error occurs:
"OSError: xkeyC/whisper-large-v3-turbo-gguf does not appear to have a file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt or flax_model.msgpack."

This model works with candle-transformers 'https://github.com/huggingface/candle/blob/main/candle-transformers/src/models/whisper/quantized_model.rs'

For python transformers, you may have to load it manually from file.

Sign up or log in to comment