archiki/robust-e2e-asr

This repository contains the code for our upcoming paper An Investigation of End-to-End Models for Robust Speech Recognition at ICASSP 2021.

robust-e2e-asr's Issues

some questions

I first run the librispeech.py and download the librispeech dataset.
Then I run the trainEnhanced.py, it shows that ModuleNotFoundError: No module named 'logger'. I really didn't find out where logger.py is. So I commented out the code about logger.
But now show FileNotFoundError: [Errno 2] No such file or directory: 'labels.json'.
How should I solve the problem?

Dataset file not exit

Sorry for interrupting, but when I want to download the custom noise dataset, the page is gone, if the author can update it, I would really appreciate for that!!

csv file

When I run the trainTLNoisy.py, it shows that FileNotFoundError: [Errno 2] No such file or directory: 'data/train_manifest.csv' .
I follow the README.md but it does not mention about it.
Did I miss it somewhere? How can I to Generate it?
Thank you!

about the training details and asking for model checkpoint

Hi @archiki,
I appreciate this work very much, and thanks for providing the implementation. Could you please tell me that how long does the training cost? BTW, did you take the model checkpoint trained from clean corpus as the initial parameters to train the robust ASR? May I ask your checkpoints?

best,
Chi-Chang Lee

Testing failed when reproducing experiments by processing test*.py

Hi @archiki,
I am trying to evaluate the model checkpoint you provided here by running the commands below.

# 1.
python test.py --test-manifest data/libri_test_clean_manifest.csv --SNR-start 0 --SNR-stop 20 --SNR-step 5
# 2.
python test_enhanced.py --test-manifest data/libri_test_clean_manifest.csv --SNR-start 0 --SNR-stop 20 --SNR-step 5
# 3.
python test_noisy.py --test-manifest data/libri_test_clean_manifest.csv --SNR-start 0 --SNR-stop 20 --SNR-step 5

The command is based on here, and the difference between the commands above is only the testing script.
All of them throw exceptions and the error messages are:

# 1. 
Traceback (most recent call last):
  File "test.py", line 7, in <module>
    from data.data_loader_specAugment import SpectrogramDataset, AudioDataLoader
ModuleNotFoundError: No module named 'data.data_loader_specAugment'

# 2.
Traceback (most recent call last):
  File "test_enhanced.py", line 11, in <module>
    from utils_orig import load_model
ModuleNotFoundError: No module named 'utils_orig'

# 3.
Traceback (most recent call last):
  File "test_noisy.py", line 203, in <module>
    half=args.half, wer_dict= wer_dict,ifNoiseClassifier=args.ifNoiseClassifier,noise_model=noise_model,ifNoiseBinary=args.binary_noisy, print_summary=True)
  File "test_noisy.py", line 92, in evaluate
    out, output_sizes = model(inputs, input_sizes)
ValueError: too many values to unpack (expected 2)

Though I can modify the files to pass these exceptions, it will take time to find the way to reproduce experiment result provided in the table...

So, my question is

1. Is the command right?
2. Which test.py is the script to reproduce the experiment result in the table?

best,
Cheng-Hung Hu

where is model*.py

I can not find model.py, model_split.py, model_split_adversary.py