MCPcopy Create free account
hub / github.com/Honee-W/FlowSE / get_tokenizer

Function get_tokenizer

model/model_utils.py:41–70  ·  view source on GitHub ↗

tokenizer - "pinyin" do g2p for only chinese characters, need .txt vocab_file - "char" for char-wise tokenizer, need .txt vocab_file - "byte" for utf-8 tokenizer - "custom" if you're directly passing in a path to the vocab.txt you want to use

(dataset_name, tokenizer: str = "pinyin",tokenizer_path="Emilia_ZH_EN_pinyin/vocab.txt")

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 2

main_workerFunction · 0.90
runFunction · 0.90

Calls

no outgoing calls

Tested by

no test coverage detected