Kyubyong / dc_tts

A TensorFlow Implementation of DC-TTS: yet another text-to-speech model

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Error at train.py 1

b29b opened this issue · comments

i tried this in colab with LJSpeech, tensorflow 1.x, python3. prepro.py ran without errors and got stuck at

python train.py 1

Traceback (most recent call last):
File "/tensorflow-1.15.2/python3.6/tensorflow_core/python/ops/script_ops.py", line 235, in __call__ ret = func(*args)
File "/content/dc_tts/data_load.py", line 107, in _load_spectrograms mel = "mels/{}".format(fname.replace("wav", "npy"))
TypeError: a bytes-like object is required, not 'str'

a897f6a
used the fix here, ram fills up before training finishes... 😔