install CPython version monotonic_align before train, test=tts

examples/csmsc/vits/local/synthesize.sh

@@ -15,4 +15,4 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
         --phones_dict=dump/phone_id_map.txt \
         --test_metadata=dump/test/norm/metadata.jsonl \
         --output_dir=${train_output_path}/test
-fi
+fi

examples/csmsc/vits/local/train.sh

@@ -3,6 +3,11 @@
 config_path=$1
 train_output_path=$2
 
+# install monotonic_align
+cd ${MAIN_ROOT}/paddlespeech/t2s/models/vits/monotonic_align
+python3 setup.py build_ext --inplace
+cd -
+
 python3 ${BIN_DIR}/train.py \
     --train-metadata=dump/train/norm/metadata.jsonl \
     --dev-metadata=dump/dev/norm/metadata.jsonl \