Deploy to Production with C++ backend

NeMo-text-processing provides tools to deploy TN and ITN for production [TEXTPROCESSING-DEPLOYMENT2]. It uses Sparrowhawk [TEXTPROCESSING-DEPLOYMENT1] – an open-source C++ framework by Google. The grammars written with NeMo-text-processing can be exported into an OpenFST Archive File (FAR) and dropped into Sparrowhawk.

• nemo_text_processing package

• Docker

• NeMo-text-processing source code

Examples how to run:

            

            
# export English TN grammars and return prompt inside docker container
cd NeMo-text-processing/tools/text_processing_deployment
bash export_grammars.sh --GRAMMARS=tn_grammars --LANGUAGE=en --INPUT_CASE=cased

# export English ITN grammars and return prompt inside docker container
cd NeMo-text-processing/tools/text_processing_deployment
bash export_grammars.sh --GRAMMARS=itn_grammars --LANGUAGE=en
        

Arguments:

• GRAMMARS - tn_grammars or itn_grammars to export either TN or ITN grammars.

• LANGUAGE - en for English. Click here for full list of languages.

• INPUT_CASE - cased or lower_cased (ITN has no differentiation between these two, only used for TN).

• MODE - By default export which returns prompt inside the docker. If --MODE=test runs NeMo-text-processing pytests inside container.

• OVERWRITE_CACHE - Whether to re-export grammars or load from cache. By default True.

• FORCE_REBUILD - Whether to rebuild docker image in cased of updated dependencies. By default False.

export_grammars.sh runs the following steps in sequence:

Go to script folder:

            

            
cd NeMo-text-processing/tools/text_processing_deployment
        

1. Grammars written in Python are exported to OpenFST archive files (FAR). Specifically, grammars ClassifyFst and VerbalizeFst from nemo_text_processing are exported and saved to ./LANGUAGE/classify/tokenize_and_classify.far and ./LANGUAGE/verbalize/verbalize.far respectively.

            

            
python pynini_export.py <--output_dir .> <--grammars GRAMMARS> <--input_case INPUT_CASE> <--language LANGUAGE>
        

2. Docker image is built with dependencies, including Thrax and Sparrowhawk.

            

            
bash docker/build.sh
        

3. Plugs in grammars into production backend by mounting grammar directory LANGUAGE/classify/ and LANGUAGE/verbalize/ inside docker. Returns docker prompt.

            

            
# launch container with the exported grammars
bash docker/launch.sh
        

4. Runs system in docker container.

            

            
echo "ITN result: two dollars fifty. TN result:$2.50" | ../../src/bin/normalizer_main --config=sparrowhawk_configuration.ascii_proto
        

This returns “ITN result: $2.50. TN result: two dollars fifty cents”

See WFST Resources for more details.

[TEXTPROCESSING-DEPLOYMENT1]

Alexander Gutkin, Linne Ha, Martin Jansche, Knot Pipatsrisawat, and Richard Sproat. Tts for low resource languages: a bangla synthesizer. In 10th Language Resources and Evaluation Conference. 2016.

[TEXTPROCESSING-DEPLOYMENT2]

Yang Zhang, Evelina Bakhturina, Kyle Gorman, and Boris Ginsburg. Nemo inverse text normalization: from development to production. 2021. arXiv:2104.05055.