WaveRNN preprocess error。HParams not configured yet.Call self.configure().

preprocess error。HParams not configured yet.Call self.configure().

Open winterwindwang opened this issue 5 years ago • 4 comments

I run the wavernn on windows.I download the LJSpeech dataset and decomposed it. After that, I edit the hparams.py, point thee decomposed path to wav_path attribute. then I run preprocess.py. it raises an error: `RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.

and then i modify preprocess.py by add "if __name__ == '__main__':",it raise the error:multiprocessing.pool.RemoteTraceback: """ Traceback (most recent call last): File "D:\Anaconda3\envs\ML_WDH\lib\multiprocessing\pool.py", line 119, in worker result = (True, func(*args, **kwds)) File "E:...\WaveRNN-master\preprocess.py", line 23, in process_wav m, x = convert_file(path) File "E:...\WaveRNN-master\preprocess.py", line 30, in convert_file y = load_wav(path) File "E:...\WaveRNN-master\utils\dsp.py", line 19, in load_wav return librosa.load(path, sr=hp.sample_rate)[0] File "E:...\WaveRNN-master\utils_init_.py", line 53, in getattr raise AttributeError("HParams not configured yet. Call self.configure()") AttributeError: HParams not configured yet. Call self.configure() """

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "E:/.../WaveRNN-master/preprocess.py", line 89, in for i, (item_id, length) in enumerate(pool.imap_unordered(process_wav, wav_files), 1): File "D:\Anaconda3\envs\ML_WDH\lib\multiprocessing\pool.py", line 735, in next raise value AttributeError: HParams not configured yet. Call self.configure()` anyone can tell me how can i fix this error.