Merge pull request #4644 from hieuthi/update_vivos_url

Update VIVOS download link
espnet · Sep 24, 2022 · 6a46986 · 6a46986
2 parents 125f377 + 4c1ad85
commit 6a46986
Show file tree

Hide file tree

Showing 5 changed files with 5 additions and 5 deletions.
diff --git a/egs/README.md b/egs/README.md
@@ -68,7 +68,7 @@ See: https://espnet.github.io/espnet/tutorial.html
 | tweb                    | The World English Bible                                      | TTS                                        | EN             | https://www.kaggle.com/bryanpark/the-world-english-bible-speech-dataset                      |                               |
 | vais1000                | VAIS-1000                                                    | TTS                                        | VI             | https://ieee-dataport.org/documents/vais-1000-vietnamese-speech-synthesis-corpus  |             |
 | vcc20                 | Voice Conversion Challenge 2020                              | VC                                         | EN->{EN, DE, FI, ZH} | http://www.vc-challenge.org/                               |                               |
-| vivos                   | VIVOS (Vietnamese corpus for ASR)                            | ASR                                        | VI             | https://ailab.hcmus.edu.vn/vivos/                            |                               |
+| vivos                   | VIVOS (Vietnamese corpus for ASR)                            | ASR                                        | VI             | https://doi.org/10.5281/zenodo.7068130                            |                               |
 | voxforge                | VoxForge                                                     | ASR                                        | 7 languages    | http://www.voxforge.org/                                     |                               |
 | wsj                     | CSR-I (WSJ0) Complete, CSR-II (WSJ1) Complete                | ASR                                        | EN             | https://catalog.ldc.upenn.edu/LDC93S6A,https://catalog.ldc.upenn.edu/LDC94S13A |                               |
 | wsj_mix                 | MERL WSJ0-mix multi-speaker dataset                          | Multispeaker ASR                           | EN             | http://www.merl.com/demos/deep-clustering                    |                               |

diff --git a/egs/vivos/README.txt b/egs/vivos/README.txt
@@ -1 +1 @@
-VIVOS is a small open Vietnamese speech corpus (15 hours) prepared by AILAB - VNUHCM University of Science for testing speech recognition. Speech data are sampled at 16kHz. It is available for downloading at https://ailab.hcmus.edu.vn/vivos/
+VIVOS is a small open Vietnamese speech corpus (15 hours) prepared by AILAB - VNUHCM University of Science for testing speech recognition. Speech data are sampled at 16kHz. It is available for downloading at https://doi.org/10.5281/zenodo.7068130 (The old url, https://ailab.hcmus.edu.vn/vivos/, is no longer maintained)
diff --git a/egs/vivos/asr1/run.sh b/egs/vivos/asr1/run.sh
@@ -42,7 +42,7 @@ use_valbest_average=false
 # data
 datadir=./downloads
 vivos_root=${datadir}/vivos
-data_url=https://ailab.hcmus.edu.vn/assets/vivos.tar.gz
+data_url=https://zenodo.org/api/files/a3a96378-5e63-4bf3-8fa6-fe2bebc871c7/vivos.tar.gz
 
 # exp tag
 tag=""

diff --git a/egs2/README.md b/egs2/README.md
@@ -109,7 +109,7 @@ See: https://espnet.github.io/espnet/espnet2_tutorial.html#recipes-using-espnet2
 | tsukuyomi               | つくよみちゃんコーパス                                                                                | TTS                     | JPN                  | https://tyc.rei-yumesaki.net/material/corpus                                                                 |              |
 | vctk                    | English Multi-speaker Corpus for CSTR Voice Cloning Toolkit                                                                      | ASR/TTS                 | ENG                  | http://www.udialogue.org/download/cstr-vctk-corpus.html                                                      |              |
 | vctk_noisyreverb        | Noisy reverberant speech database (48kHz)                                                                                        | SE                      | ENG                  | https://datashare.ed.ac.uk/handle/10283/2826                                                                 |              |
-| vivos                   | VIVOS (Vietnamese corpus for ASR)                                                                                                | ASR                     | VIE                  | https://ailab.hcmus.edu.vn/vivos/                                                                            |              |
+| vivos                   | VIVOS (Vietnamese corpus for ASR)                                                                                                | ASR                     | VIE                  | https://doi.org/10.5281/zenodo.7068130                                                                            |              |
 | voxforge                | VoxForge                                                                                                                         | ASR                     | 7 languages          | http://www.voxforge.org/                                                                                     |              |
 | wenetspeech             | WenetSpeech: A 10000+ Hours Multi-domain Chinese Corpus for Speech Recognition                                                   | ASR                     | CMN                  | https://wenet-e2e.github.io/WenetSpeech/                                                                     |              |
 | wham                    | The WSJ0 Hipster Ambient Mixtures (WHAM!) dataset                                                                                | SE                      | ENG                  | https://wham.whisper.ai/                                                                                     |              |

diff --git a/egs2/vivos/asr1/local/data.sh b/egs2/vivos/asr1/local/data.sh
@@ -27,7 +27,7 @@ fi
 
 datadir=${VIVOS}
 vivos_root=${datadir}/vivos
-data_url=https://ailab.hcmus.edu.vn/assets/vivos.tar.gz
+data_url=https://zenodo.org/api/files/a3a96378-5e63-4bf3-8fa6-fe2bebc871c7/vivos.tar.gz
 
 ndev_utt=100