Add prosody prediction in synthesize_e2e, test=tts

examples/csmsc/tts3_rhy/README.md

@@ -0,0 +1,74 @@
+# This example mainly follows the FastSpeech2 with CSMSC
+This example contains code used to train a rhythm version of [Fastspeech2](https://arxiv.org/abs/2006.04558) model with [Chinese Standard Mandarin Speech Copus](https://www.data-baker.com/open_source.html).
+
+## Dataset
+### Download and Extract
+Download CSMSC from it's [Official Website](https://test.data-baker.com/data/index/TNtts/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
+
+### Get MFA Result and Extract
+We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for fastspeech2.
+You can directly download the rhythm version of MFA result from here [baker_alignment_tone.zip](https://paddlespeech.bj.bcebos.com/Rhy_e2e/baker_alignment_tone.zip), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
+Remember in our repo, you should add `--rhy-with-duration` flag to obtain the rhythm information.
+
+## Get Started
+Assume the path to the dataset is `~/datasets/BZNSYP`.
+Assume the path to the MFA result of CSMSC is `./baker_alignment_tone`.
+Run the command below to
+1. **source path**.
+2. preprocess the dataset.
+3. train the model.
+4. synthesize wavs.
+    - synthesize waveform from `metadata.jsonl`.
+    - synthesize waveform from a text file.
+5. inference using the static model.
+```bash
+./run.sh
+```
+You can choose a range of stages you want to run, or set `stage` equal to `stop-stage` to use only one stage, for example, running the following command will only preprocess the dataset.
+```bash
+./run.sh --stage 0 --stop-stage 0
+```
+### Data Preprocessing
+```bash
+./local/preprocess.sh ${conf_path}
+```
+When it is done. A `dump` folder is created in the current directory. The structure of the dump folder is listed below.
+
+```text
+dump
+├── dev
+│   ├── norm
+│   └── raw
+├── phone_id_map.txt
+├── speaker_id_map.txt
+├── test
+│   ├── norm
+│   └── raw
+└── train
+    ├── energy_stats.npy
+    ├── norm
+    ├── pitch_stats.npy
+    ├── raw
+    └── speech_stats.npy
+```
+The dataset is split into 3 parts, namely `train`, `dev`, and` test`, each of which contains a `norm` and `raw` subfolder. The raw folder contains speech、pitch and energy features of each utterance, while the norm folder contains normalized ones. The statistics used to normalize features are computed from the training set, which is located in `dump/train/*_stats.npy`.
+
+Also, there is a `metadata.jsonl` in each subfolder. It is a table-like file that contains phones, text_lengths, speech_lengths, durations, the path of speech features, the path of pitch features, the path of energy features, speaker, and the id of each utterance.
+
+# More details can be refered to the example of FastSpeech2 with CSMSC(tts3)
+
+## Pretrained Model
+Pretrained FastSpeech2 model for end-to-end rhythm version:
+- [fastspeech2_rhy_csmsc_ckpt_1.3.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_rhy_csmsc_ckpt_1.3.0.zip)
+
+This FastSpeech2 checkpoint contains files listed below.
+```text
+fastspeech2_rhy_csmsc_ckpt_1.3.0
+├── default.yaml             # default config used to train fastspeech2
+├── phone_id_map.txt         # phone vocabulary file when training fastspeech2
+├── snapshot_iter_153000.pdz # model parameters and optimizer states
+├── durations.txt            # the intermediate output of preprocess.sh
+├── energy_stats.npy
+├── pitch_stats.npy
+└── speech_stats.npy         # statistics used to normalize spectrogram when training fastspeech2
+```

examples/csmsc/tts3_rhy/conf/default.yaml

@@ -0,0 +1 @@
+../../tts3/conf/default.yaml

examples/csmsc/tts3_rhy/local/preprocess.sh

@@ -0,0 +1 @@
+../../tts3/local/preprocess.sh

examples/csmsc/tts3_rhy/local/synthesize.sh

@@ -0,0 +1 @@
+../../tts3/local/synthesize.sh

examples/csmsc/tts3_rhy/local/synthesize_e2e.sh

@@ -0,0 +1,119 @@
+#!/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 ${BIN_DIR}/../synthesize_e2e.py \
+        --am=fastspeech2_csmsc \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_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 \
+        --use_rhy=True
+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 ${BIN_DIR}/../synthesize_e2e.py \
+        --am=fastspeech2_csmsc \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_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 \
+        --use_rhy=True
+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 ${BIN_DIR}/../synthesize_e2e.py \
+        --am=fastspeech2_csmsc \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_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 \
+        --use_rhy=True
+        # --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 ${BIN_DIR}/../synthesize_e2e.py \
+        --am=fastspeech2_csmsc \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_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 \
+        --use_rhy=True
+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 ${BIN_DIR}/../synthesize_e2e.py \
+        --am=fastspeech2_csmsc \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_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 \
+        --use_rhy=True
+fi

examples/csmsc/tts3_rhy/local/train.sh

@@ -0,0 +1 @@
+../../tts3/local/train.sh

examples/csmsc/tts3_rhy/path.sh

@@ -0,0 +1 @@
+../tts3/path.sh

examples/csmsc/tts3_rhy/run.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+
+set -e
+source path.sh
+
+gpus=0,1
+stage=0
+stop_stage=100
+
+conf_path=conf/default.yaml
+train_output_path=exp/default
+ckpt_name=snapshot_iter_153.pdz
+
+# with the following command, you can choose the stage range you want to run
+# such as `./run.sh --stage 0 --stop-stage 0`
+# this can not be mixed use with `$1`, `$2` ...
+source ${MAIN_ROOT}/utils/parse_options.sh || exit 1
+
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+    # prepare data
+    ### please place the mfa result of rhythm here
+    ./local/preprocess.sh ${conf_path} || exit -1
+fi
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    # train model, all `ckpt` under `train_output_path/checkpoints/` dir
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${train_output_path} || exit -1
+fi
+
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+    # synthesize, vocoder is pwgan by default
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
+fi
+
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+    # synthesize_e2e, vocoder is pwgan by default
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
+fi

paddlespeech/resource/pretrained_models.py

@@ -1658,3 +1658,16 @@
         },
     },
 }
+
+# ---------------------------------
+# ------------- Rhy_frontend ---------------
+# ---------------------------------
+rhy_frontend_models = {
+    'rhy_e2e': {
+        '1.0': {
+            'url':
+            'https://paddlespeech.bj.bcebos.com/Rhy_e2e/rhy_frontend.zip',
+            'md5': '6624a77393de5925d5a84400b363d8ef',
+        },
+    },
+}

paddlespeech/t2s/exps/syn_utils.py

@@ -163,10 +163,13 @@ def get_test_dataset(test_metadata: List[Dict[str, Any]],
 # frontend
 def get_frontend(lang: str='zh',
                  phones_dict: Optional[os.PathLike]=None,
-                 tones_dict: Optional[os.PathLike]=None):
+                 tones_dict: Optional[os.PathLike]=None,
+                 use_rhy=False):
     if lang == 'zh':
         frontend = Frontend(
-            phone_vocab_path=phones_dict, tone_vocab_path=tones_dict)
+            phone_vocab_path=phones_dict,
+            tone_vocab_path=tones_dict,
+            use_rhy=use_rhy)
     elif lang == 'en':
         frontend = English(phone_vocab_path=phones_dict)
     elif lang == 'mix':

paddlespeech/t2s/exps/synthesize_e2e.py

@@ -27,6 +27,7 @@
 from paddlespeech.t2s.exps.syn_utils import get_voc_inference
 from paddlespeech.t2s.exps.syn_utils import run_frontend
 from paddlespeech.t2s.exps.syn_utils import voc_to_static
+from paddlespeech.t2s.utils import str2bool
 
 
 def evaluate(args):
@@ -49,7 +50,8 @@ def evaluate(args):
     frontend = get_frontend(
         lang=args.lang,
         phones_dict=args.phones_dict,
-        tones_dict=args.tones_dict)
+        tones_dict=args.tones_dict,
+        use_rhy=args.use_rhy)
     print("frontend done!")
 
     # acoustic model
@@ -240,6 +242,11 @@ def parse_args():
         type=str,
         help="text to synthesize, a 'utt_id sentence' pair per line.")
     parser.add_argument("--output_dir", type=str, help="output dir.")
+    parser.add_argument(
+        "--use_rhy",
+        type=str2bool,
+        default=False,
+        help="run rhythm frontend or not")
 
     args = parser.parse_args()
     return args

paddlespeech/t2s/frontend/rhy_prediction/__init__.py

@@ -0,0 +1,14 @@
+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from .rhy_predictor import *