Dav Karamyan
Dav Karamyan
@evilc3 Yes it is possible to add new tokens into sentencepiece tokenizer. Here is a code. ``` # Installation # 1. pip install sentencepiece # 2. pip install protobuf #...
@qmac In paper (https://arxiv.org/pdf/2104.11348v3.pdf), the reported WER is 11.3. Does this include filler words? Is there any script that I can use to reproduce paper result using Rev .nlp output...
with a fixed high probability.