diff --git a/.compute b/.compute index adc7aa4c..47d3419d 100644 --- a/.compute +++ b/.compute @@ -1,5 +1,7 @@ #!/bin/bash +ls ${SHARED_DIR}/data/keithito pip3 install https://download.pytorch.org/whl/cu100/torch-1.0.1.post2-cp36-cp36m-linux_x86_64.whl yes | apt-get install espeak python3 setup.py develop -python3 train.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/Blizzard/Nancy/ --debug true +# python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/keithito/LJSpeech-1.1/ --restore_path ${USER_DIR}/best_model.pth.tar +python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/keithito/LJSpeech-1.1/ \ No newline at end of file diff --git a/datasets/TTSDataset.py b/datasets/TTSDataset.py index f4c70c00..497b9b2c 100644 --- a/datasets/TTSDataset.py +++ b/datasets/TTSDataset.py @@ -65,7 +65,7 @@ class MyDataset(Dataset): self.phoneme_language = phoneme_language self.verbose = verbose if use_phonemes and not os.path.isdir(phoneme_cache_path): - os.makedirs(phoneme_cache_path) + os.makedirs(phoneme_cache_path, exist_ok=True) if self.verbose: print("\n > DataLoader initialization") print(" | > Data path: {}".format(root_path)) @@ -91,7 +91,15 @@ class MyDataset(Dataset): file_name = os.path.basename(wav_file).split('.')[0] tmp_path = os.path.join(self.phoneme_cache_path, file_name+'_phoneme.npy') if os.path.isfile(tmp_path): - text = np.load(tmp_path) + try: + text = np.load(tmp_path) + except: + print(" > ERROR: phoneme connot be loaded for {}. Recomputing.".format(wav_file)) + text = np.asarray( + phoneme_to_sequence( + text, [self.cleaners], language=self.phoneme_language), + dtype=np.int32) + np.save(tmp_path, text) else: text = np.asarray( phoneme_to_sequence(text, [self.cleaners], language=self.phoneme_language), dtype=np.int32)