From 1d8ffac1d3ee4e2acb91d659384da525c3d770f7 Mon Sep 17 00:00:00 2001 From: Mostafa Ghorbandoost Date: Mon, 24 Apr 2023 16:23:16 -0700 Subject: [PATCH] Fix an invalid link in get_data.py of ljspeech (#6456) Usage of the link in line 63 leads to downloading a html file not a tsv file, so we need to change it to a raw link. Signed-off-by: Mostafa Ghorbandoost --- scripts/dataset_processing/tts/ljspeech/get_data.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/dataset_processing/tts/ljspeech/get_data.py b/scripts/dataset_processing/tts/ljspeech/get_data.py index 7c28fb8ef903..d8a0b1c2834c 100644 --- a/scripts/dataset_processing/tts/ljspeech/get_data.py +++ b/scripts/dataset_processing/tts/ljspeech/get_data.py @@ -60,7 +60,7 @@ def __extract_file(filepath, data_dir): def __process_data(data_root, whitelist_path): if whitelist_path is None: wget.download( - "https://github.com/NVIDIA/NeMo-text-processing/blob/main/nemo_text_processing/text_normalization/en/data/whitelist/lj_speech.tsv", + "https://raw.githubusercontent.com/NVIDIA/NeMo-text-processing/main/nemo_text_processing/text_normalization/en/data/whitelist/lj_speech.tsv", out=str(data_root), ) whitelist_path = data_root / "lj_speech.tsv"