Hello! I'm trying to train a tts model with my own voice and I've set up the config and metadata, recorded voicelines etc., but when I try to use compute_statistics.py to generate a scale_stats.py, I get this error:
Traceback (most recent call last):
File "C:\Python311\Lib\site-packages\TTS\bin\compute_statistics.py", line 96, in <module>
main()
File "C:\Python311\Lib\site-packages\TTS\bin\compute_statistics.py", line 44, in main
dataset_items = load_tts_samples(CONFIG.datasets)[0] # take only train data
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\TTS\tts\datasets\__init__.py", line 118, in load_tts_samples
formatter = _get_formatter_by_name(formatter_name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\TTS\tts\datasets\__init__.py", line 166, in _get_formatter_by_name
return getattr(thismodule, name.lower())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: module 'TTS.tts.datasets' has no attribute ''
I don't know, what the error is here, because I have defined a dataset in the config and I don't know, if it has something to do with the config or any other file that this process relies on.
Hello! I'm trying to train a tts model with my own voice and I've set up the config and metadata, recorded voicelines etc., but when I try to use compute_statistics.py to generate a scale_stats.py, I get this error:
I don't know, what the error is here, because I have defined a dataset in the config and I don't know, if it has something to do with the config or any other file that this process relies on.