[examples] fixed dataset download link may not reachabel about voxcon…

…verse (#288) * fixed download url may not work and fixed result typos * remove unuseful file * typos fixed * typos fixed * remove result.txt * fixed * add pre-commit hooks * fixed * fixed * fixed --------- Co-authored-by: shanguanma <[email protected]>
wenet-e2e · Mar 14, 2024 · 3013178 · 3013178
1 parent 1a6ca8c
commit 3013178
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 5 deletions.
diff --git a/examples/voxconverse/v2/README.md b/examples/voxconverse/v2/README.md
@@ -27,7 +27,7 @@
 
     | system | MISS | FA | SC | DER |
     |:---|:---:|:---:|:---:|:---:|
-    | This repo (with system SAD) | 4.0 | 2.4 | 3.5 | 9.8 |
+    | This repo (with system SAD) | 4.0 | 2.4 | 3.4 | 9.8 |
 
 
 [^1]: Spot the conversation: speaker diarisation in the wild, https://arxiv.org/pdf/2007.01216.pdf
diff --git a/examples/voxconverse/v2/path.sh b/examples/voxconverse/v2/path.sh
diff --git a/examples/voxconverse/v2/run.sh b/examples/voxconverse/v2/run.sh
@@ -56,19 +56,27 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
     unzip -o data/voxconverse_master.zip -d data
 
     # Download annotations from VoxSRC-23 validation toolkit (looks like version 0.0.2)
-    #cd data && git clone https://github.com/JaesungHuh/VoxSRC2023.git --recursive && cd -
+    # cd data && git clone https://github.com/JaesungHuh/VoxSRC2023.git --recursive && cd -
 
     # Download dev audios
     mkdir -p data/dev
-    wget -c https://mm.kaist.ac.kr/datasets/voxconverse/data/voxconverse_dev_wav.zip -O data/voxconverse_dev_wav.zip
+
+    #wget --no-check-certificate -c https://mm.kaist.ac.kr/datasets/voxconverse/data/voxconverse_dev_wav.zip -O data/voxconverse_dev_wav.zip
+    # The above url may not be reachable, you can try the link below.
+    # This url is from https://github.com/joonson/voxconverse/blob/master/README.md
+    wget --no-check-certificate -c https://www.robots.ox.ac.uk/~vgg/data/voxconverse/data/voxconverse_dev_wav.zip -O data/voxconverse_dev_wav.zip
     unzip -o data/voxconverse_dev_wav.zip -d data/dev
 
     # Create wav.scp for dev audios
     ls `pwd`/data/dev/audio/*.wav | awk -F/ '{print substr($NF, 1, length($NF)-4), $0}' > data/dev/wav.scp
 
     # Test audios
     mkdir -p data/test
-    wget -c https://mm.kaist.ac.kr/datasets/voxconverse/data/voxconverse_test_wav.zip -O data/voxconverse_test_wav.zip
+
+    #wget --no-check-certificate -c https://mm.kaist.ac.kr/datasets/voxconverse/data/voxconverse_test_wav.zip -O data/voxconverse_test_wav.zip
+    # The above url may not be reachable, you can try the link below.
+    # This url is from https://github.com/joonson/voxconverse/blob/master/README.md
+    wget  --no-check-certificate -c https://www.robots.ox.ac.uk/~vgg/data/voxconverse/data/voxconverse_test_wav.zip -O data/voxconverse_test_wav.zip
     unzip -o data/voxconverse_test_wav.zip -d data/test
 
     # Create wav.scp for test audios
@@ -161,7 +169,6 @@ fi
 if [ ${stage} -le 8 ] && [ ${stop_stage} -ge 8 ]; then
     ref_dir=data/voxconverse-master/
     #ref_dir=data/VoxSRC2023/voxconverse/
-
     echo -e "Get the DER results\n..."
     perl external_tools/SCTK-2.4.12/src/md-eval/md-eval.pl \
          -c 0.25 \