tfjs: Can not convert TensorFlow model to TensorFlowJS: Unsupported Ops in the model before optimization

Hi, I work on VS Code and we are trying to use TensorFlow for automatic programming language classification based on file content. To be concise, we need this working in a browser, thus we would like to use TensorFlowJS, and we would like to reuse this TensorFlow model https://github.com/yoeo/guesslang/tree/master/guesslang/data/model We are trying to convert this Model to a TensorFlowJs model using your conversion scripts and we are hitting the following issue:

$ tensorflowjs_wizard
2021-03-17 23:39:53.238316: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2021-03-17 23:39:53.238359: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Welcome to TensorFlow.js Converter.
? Please provide the path of model file or the directory that contains model files.
If you are converting TFHub module please provide the URL. /workspaces/tfjs-notebooks/master/guesslang-master/guesslang/data/model/saved_model.pb
? What is your input model format? (auto-detected format is marked with *) Tensorflow Saved Model *
? What is tags for the saved model? serve
? What is signature name of the model? signature name: predict
? Do you want to compress the model? (this will decrease the model precision.) No compression (Higher accuracy)
? Please enter shard size (in bytes) of the weight files? 4194304
? Do you want to skip op validation?
This will allow conversion of unsupported ops,
you can implement them as custom ops in tfjs-converter. No
? Do you want to strip debug ops?
This will improve model execution performance. Yes
? Do you want to enable Control Flow V2 ops?
This will improve branch and loop execution performance. Yes
? Do you want to provide metadata?
Provide your own metadata in the form:
metadata_key:path/metadata.json
Separate multiple metadata by comma.
? Which directory do you want to save the converted model in? /workspaces/tfjs-notebooks/src/new_model
? The output already directory exists, do you want to overwrite it? Yes
converter command generated:
tensorflowjs_converter --control_flow_v2=True --input_format=tf_saved_model --metadata= --saved_model_tags=serve --signature_name=predict --strip_debug_ops=True --weight_shard_size_bytes=4194304 /workspaces/tfjs-notebooks/master/guesslang-master/guesslang/data/model /workspaces/tfjs-notebooks/src/new_model
15:34
but alas...
ValueError: Unsupported Ops in the model before optimization
SparseFillEmptyRows, StringToHashBucketFast, SparseReshape, SparseSegmentSum, SparseSegmentMean

1. Is it even possible to convert this model to TensorFlowJS?
2. Do we have something misconfigured

I am a TensorFlow beginner so I apologise for not the nicest issue. Any help is appreciated. Thank you fyi @tylerLeonhardt