训练了transformer声源模型，可与其他声码器匹配

examples/csmsc/tts1/local/preprocess.sh

@@ -0,0 +1,62 @@
+#!/bin/bash
+
+stage=1
+stop_stage=100
+
+config_path=$1
+
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+    # get durations from MFA's result
+    echo "Generate durations.txt from MFA results ..."
+    python3 ${MAIN_ROOT}/utils/gen_duration_from_textgrid.py \
+        --inputdir=./baker_alignment_tone \
+        --output=durations.txt \
+        --config=${config_path}
+fi
+
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    # extract features
+    echo "Extract features ..."
+    python3 ${BIN_DIR}/preprocess_new.py  \
+        --dataset=baker\
+        --rootdir=~/datasets/BZNSYP/ \
+        --dumpdir=dump \
+        --dur-file=durations.txt
+        --config-path=${config_path} \
+        --num-cpu=8 \
+        --cut-sil=True
+fi
+
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+    # get features' stats(mean and std)
+    echo "Get features' stats ..."
+    python3 ${MAIN_ROOT}/utils/compute_statistics.py \
+        --metadata=dump/train/raw/metadata.jsonl \
+        --field-name="speech"
+fi
+
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+    # normalize and covert phone to id, dev and test should use train's stats
+    echo "Normalize ..."
+    python3 ${BIN_DIR}/normalize.py \
+        --metadata=dump/train/raw/metadata.jsonl \
+        --dumpdir=dump/train/norm \
+        --speech-stats=dump/train/speech_stats.npy \
+        --phones-dict=dump/phone_id_map.txt \
+        --speaker-dict=dump/speaker_id_map.txt
+
+    python3 ${BIN_DIR}/normalize.py \
+        --metadata=dump/dev/raw/metadata.jsonl \
+        --dumpdir=dump/dev/norm \
+        --speech-stats=dump/train/speech_stats.npy \
+        --phones-dict=dump/phone_id_map.txt \
+        --speaker-dict=dump/speaker_id_map.txt
+
+    python3 ${BIN_DIR}/normalize.py \
+        --metadata=dump/test/raw/metadata.jsonl \
+        --dumpdir=dump/test/norm \
+        --speech-stats=dump/train/speech_stats.npy \
+        --phones-dict=dump/phone_id_map.txt \
+        --speaker-dict=dump/speaker_id_map.txt
+fi

examples/csmsc/tts1/local/synthesize.sh

@@ -0,0 +1,95 @@
+#!/bin/bash
+
+config_path=$1
+train_output_path=$2
+ckpt_name=$3
+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 ${BIN_DIR}/synthesize.py \
+        --transformer-tts-config=${config_path} \
+        --transformer-tts-checkpoint=${train_output_path}/checkpoints/${ckpt_name} \
+        --transformer-tts-stat=dump/train/speech_stats.npy \
+        --voc=pwgan_csmsc \
+        --voc_config=pwg_baker_ckpt_0.4/pwg_default.yaml \
+        --voc_ckpt=pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz \
+        --voc_stat=pwg_baker_ckpt_0.4/pwg_stats.npy \
+        --test_metadata=dump/test/norm/metadata.jsonl \
+        --output_dir=${train_output_path}/test \
+        --phones_dict=dump/phone_id_map.txt
+fi
+
+# for more GAN Vocoders
+# multi band melgan
+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 ${BIN_DIR}/../synthesize.py \
+        --transformer-tts-config=${config_path} \
+        --transformer-tts-checkpoint=${train_output_path}/checkpoints/${ckpt_name} \
+        --transformer-tts-stat=dump/train/speech_stats.npy \
+        --voc=mb_melgan_csmsc \
+        --voc_config=mb_melgan_csmsc_ckpt_0.1.1/default.yaml \
+        --voc_ckpt=mb_melgan_csmsc_ckpt_0.1.1/snapshot_iter_1000000.pdz\
+        --voc_stat=mb_melgan_csmsc_ckpt_0.1.1/feats_stats.npy \
+        --test_metadata=dump/test/norm/metadata.jsonl \
+        --output_dir=${train_output_path}/test \
+        --phones_dict=dump/phone_id_map.txt
+fi
+
+# style melgan
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize.py \
+        --transformer-tts-config=${config_path} \
+        --transformer-tts-checkpoint=${train_output_path}/checkpoints/${ckpt_name} \
+        --transformer-tts-stat=dump/train/speech_stats.npy \
+        --voc=style_melgan_csmsc \
+        --voc_config=style_melgan_csmsc_ckpt_0.1.1/default.yaml \
+        --voc_ckpt=style_melgan_csmsc_ckpt_0.1.1/snapshot_iter_1500000.pdz \
+        --voc_stat=style_melgan_csmsc_ckpt_0.1.1/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 3 ] && [ ${stop_stage} -ge 3 ]; then
+    echo "in hifigan syn"
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize.py \
+        --transformer-tts-config=${config_path} \
+        --transformer-tts-checkpoint=${train_output_path}/checkpoints/${ckpt_name} \
+        --transformer-tts-stat=dump/train/speech_stats.npy \
+        --voc=hifigan_csmsc \
+        --voc_config=hifigan_csmsc_ckpt_0.1.1/default.yaml \
+        --voc_ckpt=hifigan_csmsc_ckpt_0.1.1/snapshot_iter_2500000.pdz \
+        --voc_stat=hifigan_csmsc_ckpt_0.1.1/feats_stats.npy \
+        --test_metadata=dump/test/norm/metadata.jsonl \
+        --output_dir=${train_output_path}/test \
+        --phones_dict=dump/phone_id_map.txt
+fi
+
+# wavernn
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+    echo "in wavernn syn"
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize.py \
+        --transformer-tts-config=${config_path} \
+        --transformer-tts-checkpoint=${train_output_path}/checkpoints/${ckpt_name} \
+        --transformer-tts-stat=dump/train/speech_stats.npy \
+        --voc=wavernn_csmsc \
+        --voc_config=wavernn_csmsc_ckpt_0.2.0/default.yaml \
+        --voc_ckpt=wavernn_csmsc_ckpt_0.2.0/snapshot_iter_400000.pdz \
+        --voc_stat=wavernn_csmsc_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

examples/csmsc/tts1/local/synthesize_e2e.sh

@@ -0,0 +1,109 @@
+#!/bin/bash
+
+config_path=$1
+train_output_path=$2
+ckpt_name=$3
+
+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 ${BIN_DIR}/../synthesize_e2e.py \
+        --transformer-tts-config=${config_path} \
+        --transformer-tts-checkpoint=${train_output_path}/checkpoints/${ckpt_name} \
+        --transformer-tts-stat=dump/train/speech_stats.npy \
+        --voc=pwgan_csmsc \
+        --voc_config=pwg_baker_ckpt_0.4/pwg_default.yaml \
+        --voc_ckpt=pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz \
+        --voc_stat=pwg_baker_ckpt_0.4/pwg_stats.npy \
+        --lang=zh \
+        --text=${BIN_DIR}/../sentences.txt \
+        --output_dir=${train_output_path}/test_e2e \
+        --phones_dict=dump/phone_id_map.txt \
+        #--inference_dir=${train_output_path}/inference
+        
+fi
+
+# for more GAN Vocoders
+# multi band melgan
+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 ${BIN_DIR}/../synthesize_e2e.py \
+        --transformer-tts-config=${config_path} \
+        --transformer-tts-checkpoint=${train_output_path}/checkpoints/${ckpt_name} \
+        --transformer-tts-stat=dump/train/speech_stats.npy \
+        --voc=mb_melgan_csmsc \
+        --voc_config=mb_melgan_csmsc_ckpt_0.1.1/default.yaml \
+        --voc_ckpt=mb_melgan_csmsc_ckpt_0.1.1/snapshot_iter_1000000.pdz\
+        --voc_stat=mb_melgan_csmsc_ckpt_0.1.1/feats_stats.npy \
+        --lang=zh \
+        --text=${BIN_DIR}/../sentences.txt \
+        --output_dir=${train_output_path}/test_e2e \
+        --phones_dict=dump/phone_id_map.txt \
+        #--inference_dir=${train_output_path}/inference
+fi
+
+# the pretrained models haven't release now
+# style melgan
+# style melgan's Dygraph to Static Graph is not ready now
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize_e2e.py \
+        --transformer-tts-config=${config_path} \
+        --transformer-tts-checkpoint=${train_output_path}/checkpoints/${ckpt_name} \
+        --transformer-tts-stat=dump/train/speech_stats.npy \
+        --voc=style_melgan_csmsc \
+        --voc_config=style_melgan_csmsc_ckpt_0.1.1/default.yaml \
+        --voc_ckpt=style_melgan_csmsc_ckpt_0.1.1/snapshot_iter_1500000.pdz \
+        --voc_stat=style_melgan_csmsc_ckpt_0.1.1/feats_stats.npy \
+        --lang=zh \
+        --text=${BIN_DIR}/../sentences.txt \
+        --output_dir=${train_output_path}/test_e2e \
+        --phones_dict=dump/phone_id_map.txt
+        # --inference_dir=${train_output_path}/inference
+fi
+
+# hifigan
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+    echo "in hifigan syn_e2e"
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize_e2e.py \
+        --transformer-tts-config=${config_path} \
+        --transformer-tts-checkpoint=${train_output_path}/checkpoints/${ckpt_name} \
+        --transformer-tts-stat=dump/train/speech_stats.npy \
+        --voc=hifigan_csmsc \
+        --voc_config=hifigan_csmsc_ckpt_0.1.1/default.yaml \
+        --voc_ckpt=hifigan_csmsc_ckpt_0.1.1/snapshot_iter_2500000.pdz \
+        --voc_stat=hifigan_csmsc_ckpt_0.1.1/feats_stats.npy \
+        --lang=zh \
+        --text=${BIN_DIR}/../sentences.txt \
+        --output_dir=${train_output_path}/test_e2e \
+        --phones_dict=dump/phone_id_map.txt \
+        #--inference_dir=${train_output_path}/inference
+fi
+
+# wavernn
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+    echo "in wavernn syn_e2e"
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize_e2e.py \
+        --transformer-tts-config=${config_path} \
+        --transformer-tts-checkpoint=${train_output_path}/checkpoints/${ckpt_name} \
+        --transformer-tts-stat=dump/train/speech_stats.npy \
+        --voc=wavernn_csmsc \
+        --voc_config=wavernn_csmsc_ckpt_0.2.0/default.yaml \
+        --voc_ckpt=wavernn_csmsc_ckpt_0.2.0/snapshot_iter_400000.pdz \
+        --voc_stat=wavernn_csmsc_ckpt_0.2.0/feats_stats.npy \
+        --lang=zh \
+        --text=${BIN_DIR}/../sentences.txt \
+        --output_dir=${train_output_path}/test_e2e \
+        --phones_dict=dump/phone_id_map.txt \
+        #--inference_dir=${train_output_path}/inference
+fi

examples/csmsc/tts1/local/train.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+config_path=$1
+train_output_path=$2
+
+python3 ${BIN_DIR}/train.py \
+    --train-metadata=dump/train/norm/metadata.jsonl \
+    --dev-metadata=dump/dev/norm/metadata.jsonl \
+    --config=${config_path} \
+    --output-dir=${train_output_path} \
+    --ngpu=2 \
+    --phones-dict=dump/phone_id_map.txt