From c1395e3a051b65d6503dd1a67b3708c6c1348120 Mon Sep 17 00:00:00 2001
From: TianYuan <white-sky@qq.com>
Date: Thu, 14 Jul 2022 11:55:15 +0000
Subject: [PATCH] add synthesize for ernie_sat aishell3 and aishell3_vctk,
 test=tts

---
 .../aishell3/ernie_sat/local/synthesize.sh    | 43 ++++++++++++++++++-
 examples/aishell3/tts3/local/synthesize.sh    |  2 +-
 .../ernie_sat/local/synthesize.sh             | 43 ++++++++++++++++++-
 3 files changed, 85 insertions(+), 3 deletions(-)

diff --git a/examples/aishell3/ernie_sat/local/synthesize.sh b/examples/aishell3/ernie_sat/local/synthesize.sh
index cc1f786e..3e907427 100755
--- a/examples/aishell3/ernie_sat/local/synthesize.sh
+++ b/examples/aishell3/ernie_sat/local/synthesize.sh
@@ -1 +1,42 @@
-#!/bin/bash
\ No newline at end of file
+#!/bin/bash
+
+config_path=$1
+train_output_path=$2
+ckpt_name=$3
+
+stage=1
+stop_stage=1
+
+# 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 ${BIN_DIR}/synthesize.py \
+        --erniesat_config=${config_path} \
+        --erniesat_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --erniesat_stat=dump/train/speech_stats.npy \
+        --voc=pwgan_aishell3 \
+        --voc_config=pwg_aishell3_ckpt_0.5/default.yaml \
+        --voc_ckpt=pwg_aishell3_ckpt_0.5/snapshot_iter_1000000.pdz \
+        --voc_stat=pwg_aishell3_ckpt_0.5/feats_stats.npy \
+        --test_metadata=dump/test/norm/metadata.jsonl \
+        --output_dir=${train_output_path}/test \
+        --phones_dict=dump/phone_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 ${BIN_DIR}/synthesize.py \
+        --erniesat_config=${config_path} \
+        --erniesat_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --erniesat_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.pdz \
+        --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
+fi
diff --git a/examples/aishell3/tts3/local/synthesize.sh b/examples/aishell3/tts3/local/synthesize.sh
index d3978833..9134e042 100755
--- a/examples/aishell3/tts3/local/synthesize.sh
+++ b/examples/aishell3/tts3/local/synthesize.sh
@@ -37,7 +37,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
         --am_stat=dump/train/speech_stats.npy \
         --voc=hifigan_aishell3 \
         --voc_config=hifigan_aishell3_ckpt_0.2.0/default.yaml \
-        --voc_ckpt=hifigan_aishell3_ckpt_0.2.0/snapshot_iter_2500000.pd \
+        --voc_ckpt=hifigan_aishell3_ckpt_0.2.0/snapshot_iter_2500000.pdz \
         --voc_stat=hifigan_aishell3_ckpt_0.2.0/feats_stats.npy \
         --test_metadata=dump/test/norm/metadata.jsonl \
         --output_dir=${train_output_path}/test \
diff --git a/examples/aishell3_vctk/ernie_sat/local/synthesize.sh b/examples/aishell3_vctk/ernie_sat/local/synthesize.sh
index cc1f786e..3e907427 100755
--- a/examples/aishell3_vctk/ernie_sat/local/synthesize.sh
+++ b/examples/aishell3_vctk/ernie_sat/local/synthesize.sh
@@ -1 +1,42 @@
-#!/bin/bash
\ No newline at end of file
+#!/bin/bash
+
+config_path=$1
+train_output_path=$2
+ckpt_name=$3
+
+stage=1
+stop_stage=1
+
+# 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 ${BIN_DIR}/synthesize.py \
+        --erniesat_config=${config_path} \
+        --erniesat_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --erniesat_stat=dump/train/speech_stats.npy \
+        --voc=pwgan_aishell3 \
+        --voc_config=pwg_aishell3_ckpt_0.5/default.yaml \
+        --voc_ckpt=pwg_aishell3_ckpt_0.5/snapshot_iter_1000000.pdz \
+        --voc_stat=pwg_aishell3_ckpt_0.5/feats_stats.npy \
+        --test_metadata=dump/test/norm/metadata.jsonl \
+        --output_dir=${train_output_path}/test \
+        --phones_dict=dump/phone_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 ${BIN_DIR}/synthesize.py \
+        --erniesat_config=${config_path} \
+        --erniesat_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --erniesat_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.pdz \
+        --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
+fi