NeMo/examples/slu/speech_intent_slot 0 files were filtered totalling 0.00 hours

[yangdongdong2000]

I am trying to train a model on the SLURP dataset using the NeMo framework by following the steps outlined in the README.md file under NeMo/examples/slu/speech_intent_slot.

• Data Preparation and Building Tokenizers completed successfully.
• The .json files (ending with slu.json) were correctly generated under the slurp_data folder.

However, when I run the training script, I encounter the following error:

self._train_dl = self._setup_dataloader_from_config(config=train_data_config)
  File "/home/ddyang/miniconda3/envs/nemo/lib/python3.10/site-packages/nemo/collections/asr/models/slu_models.py", line 420, in _setup_dataloader_from_config
    return torch.utils.data.DataLoader(
  File "/home/ddyang/miniconda3/envs/nemo/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 350, in __init__
    sampler = RandomSampler(dataset, generator=generator)  # type: ignore[arg-type]
  File "/home/ddyang/miniconda3/envs/nemo/lib/python3.10/site-packages/torch/utils/data/sampler.py", line 143, in __init__
    raise ValueError(f"num_samples should be a positive integer value, but got num_samples={self.num_samples}")
ValueError: num_samples should be a positive integer value, but got num_samples=0

It seems like the data was not read correctly. Could you please guide me on how to resolve this issue?

---