# pip install git+https://github.com/huggingface/transformers --force-reinstall
# pip install git+https://github.com/bayartsogt-ya/whisper-multiple-hf-datasets

from multiple_datasets.hub_default_utils import convert_hf_whisper

convert_hf_whisper("mitchelldehaven/whisper-large-v2-ru", "large-v2-ru.pt")


# We also provide a script to convert any Whisper models compatible with the Transformers library. They could be the original OpenAI models or user fine-tuned models.
# For example the command below converts the original "large-v2" Whisper model and saves the weights in FP16:

!pip install transformers[torch]>=4.23

!ct2-transformers-converter --model openai/whisper-large-v2 --output_dir whisper-large-v2-ct2 \
    --copy_files tokenizer.json --quantization float16

# The option --model accepts a model name on the Hub or a path to a model directory.
# If the option --copy_files tokenizer.json is not used, the tokenizer configuration is automatically downloaded when the model is loaded later.