Which model to use?

#3
by tkyin - opened

Hello, I am confused by all the different models in this repo.

Am I correct in assuming that the newest onnx files uploaded around January 17th, 2025 should be used?
decoder_model_merged_quantized.onnx - 42.5 MB
encoder_model_quantized.onnx - 20.5 MB

Thanks!

tkyin changed discussion status to closed
tkyin changed discussion status to open

Sign up or log in to comment