When running train_first.py with librosa 0.10 I got error about resample call:
Original Traceback (most recent call last):
File "C:\Python310\lib\site-packages\torch\utils\data\_utils\worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "C:\Python310\lib\site-packages\torch\utils\data\_utils\fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "C:\Python310\lib\site-packages\torch\utils\data\_utils\fetch.py", line 51, in <listcomp>
data = [self.dataset[idx] for idx in possibly_batched_index]
File "E:\Work\StyleTTS\meldataset.py", line 101, in __getitem__
wave, text_tensor, speaker_id = self._load_tensor(data)
File "E:\Work\StyleTTS\meldataset.py", line 119, in _load_tensor
wave = librosa.resample(wave, sr, 24000)
TypeError: resample() takes 1 positional argument but 3 were given
Fixing it with the line 'wave = librosa.resample(wave, orig_sr=sr, target_sr=24000)'
Also fixing an issue of reading the UTF-8 file without specifying the encoding which led to an error about unknown character on Windows.
When running train_first.py with librosa 0.10 I got error about resample call:
Fixing it with the line 'wave = librosa.resample(wave, orig_sr=sr, target_sr=24000)'
Also fixing an issue of reading the UTF-8 file without specifying the encoding which led to an error about unknown character on Windows.