Hi!
So I am doing like I supposed to. I modified al required files for training my own model. But when I ran preprocess I got this error:
Traceback (most recent call last):
File "C:\Python36\lib\concurrent\futures\process.py", line 175, in _process_worker
r = call_item.fn(*call_item.args, **call_item.kwargs)
File "D:\tacotron-master\datasets\ngspeech.py", line 53, in _process_utterance
wav = audio.load_wav(wav_path)
File "D:\tacotron-master\util\audio.py", line 11, in load_wav
return librosa.core.load(path, sr=hparams.sample_rate)[0]
File "C:\Python36\lib\site-packages\librosa\core\audio.py", line 107, in load
with audioread.audio_open(os.path.realpath(path)) as input_file:
File "C:\Python36\lib\site-packages\audioread__init__.py", line 111, in audio_open
return BackendClass(path)
File "C:\Python36\lib\site-packages\audioread\rawread.py", line 62, in init
self._fh = open(filename, 'rb')
FileNotFoundError: [Errno 2] No such file or directory: 'D:\tacotron-master\NGspeech\wavs\\ufeffNGSpeech001.wav'
"""
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "preprocess.py", line 59, in
main()
File "preprocess.py", line 55, in main
preprocess_ngspeech(args)
File "preprocess.py", line 28, in preprocess_ngspeech
metadata = ngspeech.build_from_path(in_dir, out_dir, args.num_workers, tqdm=tqdm)
File "D:\tacotron-master\datasets\ngspeech.py", line 33, in build_from_path
return [future.result() for future in tqdm(futures)]
File "D:\tacotron-master\datasets\ngspeech.py", line 33, in
return [future.result() for future in tqdm(futures)]
File "C:\Python36\lib\concurrent\futures_base.py", line 432, in result
return self.get_result()
File "C:\Python36\lib\concurrent\futures_base.py", line 384, in get_result
raise self._exception
FileNotFoundError: [Errno 2] No such file or directory: 'D:\tacotron-master\NGspeech\wavs\\ufeffNGSpeech001.wav'
I have checked, all files exist. Like in the example of LJspeech. But weird is that it can't find file:\tacotron-master\NGspeech\wavs\\ufeffNGSpeech001.wav' I don't know where did it find '\ufeff' in a file path. What am I doing wrong?
Thank you
Hi! So I am doing like I supposed to. I modified al required files for training my own model. But when I ran preprocess I got this error: Traceback (most recent call last): File "C:\Python36\lib\concurrent\futures\process.py", line 175, in _process_worker r = call_item.fn(*call_item.args, **call_item.kwargs) File "D:\tacotron-master\datasets\ngspeech.py", line 53, in _process_utterance wav = audio.load_wav(wav_path) File "D:\tacotron-master\util\audio.py", line 11, in load_wav return librosa.core.load(path, sr=hparams.sample_rate)[0] File "C:\Python36\lib\site-packages\librosa\core\audio.py", line 107, in load with audioread.audio_open(os.path.realpath(path)) as input_file: File "C:\Python36\lib\site-packages\audioread__init__.py", line 111, in audio_open return BackendClass(path) File "C:\Python36\lib\site-packages\audioread\rawread.py", line 62, in init self._fh = open(filename, 'rb') FileNotFoundError: [Errno 2] No such file or directory: 'D:\tacotron-master\NGspeech\wavs\\ufeffNGSpeech001.wav' """
The above exception was the direct cause of the following exception:
Traceback (most recent call last): File "preprocess.py", line 59, in
main()
File "preprocess.py", line 55, in main
preprocess_ngspeech(args)
File "preprocess.py", line 28, in preprocess_ngspeech
metadata = ngspeech.build_from_path(in_dir, out_dir, args.num_workers, tqdm=tqdm)
File "D:\tacotron-master\datasets\ngspeech.py", line 33, in build_from_path
return [future.result() for future in tqdm(futures)]
File "D:\tacotron-master\datasets\ngspeech.py", line 33, in
return [future.result() for future in tqdm(futures)]
File "C:\Python36\lib\concurrent\futures_base.py", line 432, in result
return self.get_result()
File "C:\Python36\lib\concurrent\futures_base.py", line 384, in get_result
raise self._exception
FileNotFoundError: [Errno 2] No such file or directory: 'D:\tacotron-master\NGspeech\wavs\\ufeffNGSpeech001.wav'
I have checked, all files exist. Like in the example of LJspeech. But weird is that it can't find file:\tacotron-master\NGspeech\wavs\\ufeffNGSpeech001.wav' I don't know where did it find '\ufeff' in a file path. What am I doing wrong? Thank you
EDIT \ufeff is used in encoding -> https://github.com/clld/clldutils/issues/65