From 90cc45dd4e942926c72172b3b5f6c06250091efd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eren=20G=C3=B6lge?= Date: Wed, 1 Dec 2021 10:06:02 +0100 Subject: [PATCH] Update data loader tests --- TTS/tts/datasets/dataset.py | 17 ----------------- 1 file changed, 17 deletions(-) diff --git a/TTS/tts/datasets/dataset.py b/TTS/tts/datasets/dataset.py index 9de40c2b..d4a12c07 100644 --- a/TTS/tts/datasets/dataset.py +++ b/TTS/tts/datasets/dataset.py @@ -69,9 +69,6 @@ class TTSDataset(Dataset): samples (list): List of dataset samples. - tokenizer (TTSTokenizer): tokenizer to convert text to sequence IDs. If None init internally else - use the given. Defaults to None. - tokenizer (TTSTokenizer): tokenizer to convert text to sequence IDs. If None init internally else use the given. Defaults to None. @@ -205,20 +202,6 @@ class TTSDataset(Dataset): token_ids = self.tokenizer.text_to_ids(text) return np.array(token_ids, dtype=np.int32) - @staticmethod - def _parse_sample(item): - language_name = None - attn_file = None - if len(item) == 5: - text, wav_file, speaker_name, language_name, attn_file = item - elif len(item) == 4: - text, wav_file, speaker_name, language_name = item - elif len(item) == 3: - text, wav_file, speaker_name = item - else: - token_ids = self.tokenizer.text_to_ids(text) - return token_ids - def load_data(self, idx): item = self.samples[idx]