Closed HURIMOZ closed 3 months ago
Hi, Iʻm looking for a Python script to convert SentencePiece .vocab files to OpenNMT-py .onmt_vocab format. SentencePiece vocab files have negative values and we need positive values for the frequency of the words when using OpenNMT-py.
The numerical values in the vocab files are the score of each token. The definition depends on the model format.
exp(log prob) will be roughly equivalent to the frequency or occurrence prob.
Hi, Iʻm looking for a Python script to convert SentencePiece .vocab files to OpenNMT-py .onmt_vocab format. SentencePiece vocab files have negative values and we need positive values for the frequency of the words when using OpenNMT-py.