add hifigan in syn of aishell3, test=tts

examples/aishell3/tts3/local/synthesize.sh

@@ -4,9 +4,14 @@ config_path=$1
 train_output_path=$2
 ckpt_name=$3
 
-FLAGS_allocator_strategy=naive_best_fit \
-FLAGS_fraction_of_gpu_memory_to_use=0.01 \
-python3 ${BIN_DIR}/../synthesize.py \
+stage=0
+stop_stage=0
+
+# pwgan
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize.py \
         --am=fastspeech2_aishell3 \
         --am_config=${config_path} \
         --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
@@ -19,3 +24,24 @@ python3 ${BIN_DIR}/../synthesize.py \
         --output_dir=${train_output_path}/test \
         --phones_dict=dump/phone_id_map.txt \
         --speaker_dict=dump/speaker_id_map.txt
+fi
+
+# hifigan
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize.py \
+        --am=fastspeech2_aishell3 \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_stat=dump/train/speech_stats.npy \
+        --voc=hifigan_aishell3 \
+        --voc_config=hifigan_aishell3_ckpt_0.2.0/default.yaml \
+        --voc_ckpt=hifigan_aishell3_ckpt_0.2.0/snapshot_iter_2500000.pd \
+        --voc_stat=hifigan_aishell3_ckpt_0.2.0/feats_stats.npy \
+        --test_metadata=dump/test/norm/metadata.jsonl \
+        --output_dir=${train_output_path}/test \
+        --phones_dict=dump/phone_id_map.txt \
+        --speaker_dict=dump/speaker_id_map.txt
+fi
+

examples/aishell3/tts3/local/synthesize_e2e.sh

@@ -4,9 +4,14 @@ config_path=$1
 train_output_path=$2
 ckpt_name=$3
 
-FLAGS_allocator_strategy=naive_best_fit \
-FLAGS_fraction_of_gpu_memory_to_use=0.01 \
-python3 ${BIN_DIR}/../synthesize_e2e.py \
+stage=0
+stop_stage=0
+
+# pwgan
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize_e2e.py \
         --am=fastspeech2_aishell3 \
         --am_config=${config_path} \
         --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
@@ -22,3 +27,27 @@ python3 ${BIN_DIR}/../synthesize_e2e.py \
         --speaker_dict=dump/speaker_id_map.txt \
         --spk_id=0 \
         --inference_dir=${train_output_path}/inference
+fi
+
+# hifigan
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    echo "in hifigan syn_e2e"
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize_e2e.py \
+        --am=fastspeech2_aishell3 \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_stat=fastspeech2_nosil_aishell3_ckpt_0.4/speech_stats.npy \
+        --voc=hifigan_aishell3 \
+        --voc_config=hifigan_aishell3_ckpt_0.2.0/default.yaml \
+        --voc_ckpt=hifigan_aishell3_ckpt_0.2.0/snapshot_iter_2500000.pdz \
+        --voc_stat=hifigan_aishell3_ckpt_0.2.0/feats_stats.npy \
+        --lang=zh \
+        --text=${BIN_DIR}/../sentences.txt \
+        --output_dir=${train_output_path}/test_e2e \
+        --phones_dict=fastspeech2_nosil_aishell3_ckpt_0.4/phone_id_map.txt \
+        --speaker_dict=fastspeech2_nosil_aishell3_ckpt_0.4/speaker_id_map.txt \
+        --spk_id=0 \
+        --inference_dir=${train_output_path}/inference
+    fi