Evelina

Thanks for reporting this @hannan72! @BuyuanCui could you add the fix for `zh` in [PR112](https://github.com/NVIDIA/NeMo-text-processing/pull/112)? @mgrafu could you take a look at `ar` issue?

@hannan72 closing this one as fixed, please re-open if the error persists.

@BuyuanCui should we close this PR in favor of https://github.com/NVIDIA/NeMo-text-processing/pull/141 ?

@pirchi1 why do you suggest removing states abbreviation expansion?

@mgrafu is this PR WIP?

@BuyuanCui could you please take a look?

@lifeiteng a few options to speed up: - use `--cache_dir` - use normalize_list() https://github.com/NVIDIA/NeMo-text-processing/blob/main/nemo_text_processing/text_normalization/normalize.py#L75

@BuyuanCui https://github.com/NVIDIA/NeMo-text-processing/pull/112

@riqiang-dp we recommend Sparrowhawk for deployment https://docs.nvidia.com/nemo-framework/user-guide/latest/nemotoolkit/nlp/text_normalization/wfst/wfst_text_processing_deployment.html