From fabb3a1fd17b10cbcf252240e0c40243a8c2f971 Mon Sep 17 00:00:00 2001
From: D-Keqi <61508571+D-Keqi@users.noreply.github.com>
Date: Tue, 19 Apr 2022 16:39:39 +0800
Subject: [PATCH] update the test_integration_espnet2

---
 ci/test_integration_espnet2.sh | 37 ++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/ci/test_integration_espnet2.sh b/ci/test_integration_espnet2.sh
index 78086272af7..ac664494a6d 100755
--- a/ci/test_integration_espnet2.sh
+++ b/ci/test_integration_espnet2.sh
@@ -100,6 +100,40 @@ if python3 -c "import fairseq" &> /dev/null; then
     cd "${cwd}"
 fi
 
+# [ESPnet2] test st recipe
+cd ./egs2/mini_an4/st1
+echo "==== [ESPnet2] ST ==="
+./run.sh --stage 1 --stop-stage 1
+feats_types="raw fbank_pitch"
+token_types="bpe char"
+for t in ${feats_types}; do
+    ./run.sh --stage 2 --stop-stage 4 --feats-type "${t}" --python "${python}"
+done
+for t in ${token_types}; do
+    ./run.sh --stage 5 --stop-stage 5 --token-type "${t}" --python "${python}"
+done
+for t in ${feats_types}; do
+    for t2 in ${token_types}; do
+        echo "==== feats_type=${t}, token_types=${t2} ==="
+        ./run.sh --ngpu 0 --stage 6 --stop-stage 13 --skip-upload false --feats-type "${t}" --token-type "${t2}" \
+            --asr-args "--max_epoch=1" --lm-args "--max_epoch=1" --python "${python}"
+    done
+done
+echo "==== feats_type=raw, token_types=bpe, model_conf.extract_feats_in_collect_stats=False, normalize=utt_mvn ==="
+./run.sh --ngpu 0 --stage 10 --stop-stage 13 --skip-upload false --feats-type "raw" --token-type "bpe" \
+    --feats_normalize "utterance_mvn" --lm-args "--max_epoch=1" --python "${python}" \
+    --asr-args "--model_conf extract_feats_in_collect_stats=false --max_epoch=1"
+
+echo "==== use_streaming, feats_type=raw, token_types=bpe, model_conf.extract_feats_in_collect_stats=False, normalize=utt_mvn ==="
+./run.sh --use_streaming true --ngpu 0 --stage 6 --stop-stage 13 --skip-upload false --feats-type "raw" --token-type "bpe" \
+    --feats_normalize "utterance_mvn" --lm-args "--max_epoch=1" --python "${python}" \
+    --asr-args "--model_conf extract_feats_in_collect_stats=false --max_epoch=1 --encoder=contextual_block_transformer --decoder=transformer
+                --encoder_conf block_size=40 --encoder_conf hop_size=16 --encoder_conf look_ahead=16"
+
+# Remove generated files in order to reduce the disk usage
+rm -rf exp dump data
+cd "${cwd}"
+
 # [ESPnet2] Validate configuration files
 echo "<blank>" > dummy_token_list
 echo "==== [ESPnet2] Validation configuration files ==="
@@ -124,6 +158,9 @@ if python3 -c 'import torch as t; from distutils.version import LooseVersion as
     for f in egs2/*/ssl1/conf/train*.yaml; do
         ${python} -m espnet2.bin.hubert_train --config "${f}" --iterator_type none --normalize none --dry_run true --output_dir out --token_list dummy_token_list
     done
+    for f in egs2/*/st1/conf/train_st*.yaml; do
+        ${python} -m espnet2.bin.st_train --config "${f}" --iterator_type none --dry_run true --output_dir out --token_list dummy_token_list --src_token_list dummy_token_list
+    done
 fi
 
 # These files must be same each other.