TTS example on colab not working

[faaip]

Hi all.

I have been trying to train a voice using the TTS_example.ipynb as hosted on colab. When attempting to run the final cell:

!python train.py --config_path config.json --data_path ../LJSpeech-1.1/ | tee training.log

I get the following error message:

`
Traceback (most recent call last):
File "train.py", line 501, in
main(args)
File "train.py", line 359, in main
num_chars = len(phonemes) if c.use_phonemes else len(symbols)
AttributeError: 'AttrDict' object has no attribute 'use_phonemes'

Using CUDA: True
Number of GPUs: 1
Git Hash: dce1715
Experiment folder: /content/TTS/../keep/TTS-master-February-26-2019_01+57PM-dce1715
Setting up Audio Processor...
| > fft size: 2048, hop length: 275, win length: 1102
| > Audio Processor attributes.
| > bits:None
| > sample_rate:22050
| > num_mels:80
| > min_level_db:-100
| > frame_shift_ms:12.5
| > frame_length_ms:50
| > ref_level_db:20
| > num_freq:1025
| > power:1.5
| > preemphasis:0.97
| > griffin_lim_iters:60
| > signal_norm:True
| > symmetric_norm:False
| > mel_fmin:0
| > mel_fmax:None
| > max_norm:1.0
| > clip_norm:True
| > do_trim_silence:True
| > n_fft:2048
| > hop_length:275
| > win_length:1102
! Run is removed from /content/TTS/../keep/TTS-master-February-26-2019_01+57PM-dce1715
`

Does anyone know how this can be fixed? Thanks!

[erogol]

needs to be updated with the latest config.json

[faaip]

Thanks, @erogol . I tried using the newest config.json instead (https://github.com/mozilla/TTS/blob/master/config.json) and now get the following error:

`> Using CUDA: True

Number of GPUs: 1
Git Hash: dce1715
Experiment folder: /media/erogol/data_ssd/Data/models/ljspeech_models/queue-February-27-2019_01+02PM-dce1715
Setting up Audio Processor...
| > fft size: 2048, hop length: 275, win length: 1102
| > Audio Processor attributes.
| > bits:None
| > sample_rate:22050
| > num_mels:80
| > min_level_db:-100
| > frame_shift_ms:12.5
| > frame_length_ms:50
| > ref_level_db:20
| > num_freq:1025
| > power:1.5
| > preemphasis:0.98
| > griffin_lim_iters:60
| > signal_norm:True
| > symmetric_norm:False
| > mel_fmin:0
| > mel_fmax:None
| > max_norm:1.0
| > clip_norm:True
| > do_trim_silence:True
| > n_fft:2048
| > hop_length:275
| > win_length:1102
| > Number of characters : 61
| > Num output units : 1025

Starting a new training
| > Model has 7000370 parameters
DataLoader initialization
| > Data path: ../LJSpeech-1.1/
| > Use phonemes: True
| > phoneme language: en-us
| > Cached dataset: False
| > Number of instances : 12000
| > Max length sequence: 187
| > Min length sequence: 5
| > Avg length sequence: 98.4255
| > 0 instances are ignored (0)
| > Batch group shuffling is active.
| > Epoch 0/1000
Traceback (most recent call last):
File "train.py", line 501, in
main(args)
File "train.py", line 439, in main
scheduler, ap, epoch)
File "train.py", line 79, in train
for num_iter, data in enumerate(data_loader):
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 637, in __next__
return self._process_next_batch(batch)
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 658, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
RuntimeError: Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 138, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 138, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/content/TTS/TTS/datasets/TTSDataset.py", line 159, in __getitem__
return self.load_data(idx)
File "/content/TTS/TTS/datasets/TTSDataset.py", line 118, in load_data
text = self.load_phoneme_sequence(wav_file, text)
File "/content/TTS/TTS/datasets/TTSDataset.py", line 94, in load_phoneme_sequence
phoneme_to_sequence(text, [self.cleaners], language=self.phoneme_language), dtype=np.int32)
File "/content/TTS/TTS/utils/text/__init__.py", line 48, in phoneme_to_sequence
phonemes = text2phone(clean_text, language)
File "/content/TTS/TTS/utils/text/__init__.py", line 30, in text2phone
ph = phonemize(text, separator=seperator, strip=False, njobs=1, backend='espeak', language=language)
File "/usr/local/lib/python3.6/dist-packages/phonemizer/phonemize.py", line 90, in phonemize
backend = backendsbackend
File "/usr/local/lib/python3.6/dist-packages/phonemizer/backend.py", line 165, in __init__
super(self.__class__, self).__init__(language, logger=logger)
File "/usr/local/lib/python3.6/dist-packages/phonemizer/backend.py", line 57, in __init__
'{} not installed on your system'.format(self.name))
RuntimeError: not installed on your system

! Run is removed from /media/erogol/data_ssd/Data/models/ljspeech_models/queue-February-27-2019_01+02PM-dce1715`

How do I got about installing the Epseak backend on colab? Thanks.

[erogol]

apt-get install espeak in a colab way

[faaip]

Perfect. Thank you for your help.

[mrgloom]

Looks like for MacOS brew install espeak solves the problem.