feat: Samuel's PR suggestion

EveryVoiceTTS · Jan 24, 2025 · 5651ada · 5651ada
1 parent 194551f
commit 5651ada
Show file tree

Hide file tree

Showing 3 changed files with 27 additions and 18 deletions.
diff --git a/everyvoice/tests/regression/README.md b/everyvoice/tests/regression/README.md
@@ -2,25 +2,32 @@
 
 ## Preparing the regression training data:
 
- - Download LJ 1.1 from https://keithito.com/LJ-Speech-Dataset/
- - Download Sinhala TTS from https://openslr.org/30/
- - Download High quality TTS data for four South African languages (af, st, tn,
-   xh) from https://openslr.org/32
- - See [`prep-datasets.sh`](prep-datasets.sh) to see where these datasets are expected to be found.
- - Run this to create the regression testing directory structure:
+- Download LJ 1.1 from https://keithito.com/LJ-Speech-Dataset/
+- Download Sinhala TTS from https://openslr.org/30/
+- Download High quality TTS data for four South African languages (af, st, tn,
+  xh) from https://openslr.org/32
+- See [`prep-datasets.sh`](prep-datasets.sh) to see where these datasets are expected to be found.
+- Run this to create the regression testing directory structure:
 
-       mkdir regress-1  # or any suffix you want
-       cd regress-1
-       ../prep-datasets.sh
+```sh
+export ACTIVATE_SCRIPT=$HOME/start-ev.sh
+export SGILE_DATASET_ROOT=$HOME/sgile/data
+
+mkdir regress-1  # or any suffix you want
+cd regress-1
+../prep-datasets.sh
+```
 
 ## Running the regression tests
 
 On a Slurm cluster:
 
-    for dir in regress-*; do
-        pushd $dir
-        sbatch ../../regression-test.sh
-        popd
-    done
+```sh
+for dir in regress-*; do
+    pushd $dir
+    sbatch ../../regression-test.sh
+    popd
+done
+```
 
 Or just use `../../regression-test.sh` directly in the loop if you're not on a cluster.
diff --git a/everyvoice/tests/regression/prep-datasets.sh b/everyvoice/tests/regression/prep-datasets.sh
@@ -17,7 +17,9 @@ get_slice() {
 
 EVERYVOICE_REGRESS_ROOT=$(python -c 'import everyvoice; print(everyvoice.__path__[0])')/tests/regression
 
-LJ_SPEECH_DATASET=$HOME/sgile/data/LJSpeech-1.1
+SGILE_DATASET_ROOT=${SGILE_DATASET_ROOT:-$HOME/sgile/data}
+
+LJ_SPEECH_DATASET=$SGILE_DATASET_ROOT/LJSpeech-1.1
 LJSLICES="150 600 1600 full"
 for slice in $LJSLICES; do
     dir=regress-lj-$slice
@@ -34,7 +36,7 @@ Boo!
     echo spec > "$dir"/test2.txt
 done
 
-SinhalaTTS=$HOME/sgile/data/SinhalaTTS
+SinhalaTTS=$SGILE_DATASET_ROOT/SinhalaTTS
 dir=regress-si
 mkdir $dir
 ln -s "$SinhalaTTS/wavs" $dir/
@@ -51,7 +53,7 @@ cat <<'==EOF==' > "$dir"/test.txt
 ==EOF==
 echo "අක-ෂර" > "$dir"/test2.txt
 
-isiXhosa=$HOME/sgile/data/OpenSLR32-four-South-Afican-languages/xh_za/za/xho
+isiXhosa=$SGILE_DATASET_ROOT/OpenSLR32-four-South-Afican-languages/xh_za/za/xho
 dir=regress-xh
 mkdir $dir
 ln -s "$isiXhosa/wavs" $dir/

diff --git a/everyvoice/tests/regression/regression-test.sh b/everyvoice/tests/regression/regression-test.sh
@@ -14,7 +14,7 @@
 
 # User env config -- set ACTIVATE_SCRIPT to point to something that will activate the
 # right Python environment, or leave it empty if you don't need it.
-ACTIVATE_SCRIPT=$HOME/start_ev.sh
+ACTIVATE_SCRIPT=${ACTIVATE_SCRIPT:-$HOME/start_ev.sh}
 
 # Run a command, logging it first
 r() {