Added rhythm prediction function, test=tts

examples/other/rhy/README.md

@@ -0,0 +1,79 @@
+# Punctuation Restoration with IWLST2012-Zh
+
+## Get Started
+### Data Preprocessing
+```bash
+./run.sh --stage 0 --stop-stage 0
+```
+### Model Training
+```bash
+./run.sh --stage 1 --stop-stage 1
+```
+### Testing
+```bash
+./run.sh --stage 2 --stop-stage 2
+```
+### Punctuation Restoration
+```bash
+./run.sh --stage 3 --stop-stage 3
+```
+## Pretrained Model
+The pretrained model can be downloaded here:
+
+[ernie_linear_p3_iwslt2012_zh_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/text/ernie_linear_p3_iwslt2012_zh_ckpt_0.1.1.zip)
+
+[ernie-3.0-base.tar.gz](https://paddlespeech.bj.bcebos.com/punc_restore/ernie-3.0-base.tar.gz)
+
+[ernie-3.0-medium.tar.gz](https://paddlespeech.bj.bcebos.com/punc_restore/ernie-3.0-medium.tar.gz)
+
+[ernie-3.0-micro.tar.gz](https://paddlespeech.bj.bcebos.com/punc_restore/ernie-3.0-micro.tar.gz)
+
+[ernie-mini.tar.gz](https://paddlespeech.bj.bcebos.com/punc_restore/ernie-mini.tar.gz)
+
+[ernie-nano.tar.gz](https://paddlespeech.bj.bcebos.com/punc_restore/ernie-nano.tar.gz)
+
+[ernie-tiny.tar.gz](https://paddlespeech.bj.bcebos.com/punc_restore/ernie-tiny.tar.gz)
+
+### Test Result
+- Ernie 1.0
+    |       |COMMA  |  PERIOD | QUESTION | OVERALL|
+    |:-----:|:-----:|:-----:|:-----:|:-----:|  
+    |Precision  |0.510955  |0.526462  |0.820755  |0.619391|
+    |Recall     |0.517433  |0.564179  |0.861386  |0.647666|
+    |F1         |0.514173  |0.544669  |0.840580  |0.633141|
+- Ernie-tiny
+    |       |COMMA  |  PERIOD | QUESTION | OVERALL|
+    |:-----:|:-----:|:-----:|:-----:|:-----:|  
+    |Precision  |0.733177  |0.721448  |0.754717  |0.736447|
+    |Recall     |0.380740  |0.524646  |0.733945  |0.546443|
+    |F1         |0.501204  |0.607506  |0.744186  |0.617632|
+- Ernie-3.0-base-zh
+    |       |COMMA  |  PERIOD | QUESTION | OVERALL|
+    |:-----:|:-----:|:-----:|:-----:|:-----:|  
+    |Precision  |0.805947  |0.764160  |0.858491  |0.809532|
+    |Recall     |0.399070  |0.567978  |0.850467  |0.605838|
+    |F1         |0.533817  |0.651623  |0.854460  |0.679967|
+- Ernie-3.0-medium-zh
+    |       |COMMA  |  PERIOD | QUESTION | OVERALL|
+    |:-----:|:-----:|:-----:|:-----:|:-----:|  
+    |Precision  |0.730829  |0.699164  |0.707547  |0.712514|
+    |Recall     |0.388196  |0.533286  |0.797872  |0.573118|
+    |F1         |0.507058  |0.605062  |0.750000  |0.620707|
+- Ernie-3.0-mini-zh
+    |       |COMMA  |  PERIOD | QUESTION | OVERALL|
+    |:-----:|:-----:|:-----:|:-----:|:-----:|  
+    |Precision  |0.757433  |0.708449  |0.707547  |0.724477|
+    |Recall     |0.355752  |0.506977  |0.735294  |0.532674|
+    |F1         |0.484121  |0.591015  |0.721154  |0.598763|
+- Ernie-3.0-micro-zh
+    |       |COMMA  |  PERIOD | QUESTION | OVERALL|
+    |:-----:|:-----:|:-----:|:-----:|:-----:|  
+    |Precision  |0.733959  |0.679666  |0.726415  |0.713347|
+    |Recall     |0.332742  |0.483487  |0.712963  |0.509731|
+    |F1         |0.457896  |0.565033  |0.719626  |0.580852|
+- Ernie-3.0-nano-zh
+    |       |COMMA  |  PERIOD | QUESTION | OVERALL|
+    |:-----:|:-----:|:-----:|:-----:|:-----:|  
+    |Precision  |0.693271  |0.682451  |0.754717  |0.710146|
+    |Recall     |0.327784  |0.491968  |0.666667  |0.495473|
+    |F1         |0.445114  |0.571762  |0.707965  |0.574947|

examples/other/rhy/conf/default.yaml

@@ -0,0 +1,44 @@
+###########################################################
+#                       DATA SETTING                      #
+###########################################################
+dataset_type: Ernie
+train_path: data/rhy_predict/train.txt
+dev_path: data/rhy_predict/dev.txt
+test_path: data/rhy_predict/test.txt
+batch_size: 64
+num_workers: 2
+data_params: 
+    pretrained_token: ernie-1.0
+    punc_path: data/rhy_predict/rhy_token
+    seq_len: 100
+
+
+###########################################################
+#                       MODEL SETTING                     #
+###########################################################
+model_type: ErnieLinear
+model:
+    pretrained_token: ernie-1.0
+    num_classes: 5
+
+###########################################################
+#                     OPTIMIZER SETTING                   #
+###########################################################
+optimizer_params:
+    weight_decay: 1.0e-6               # weight decay coefficient.
+
+scheduler_params:
+    learning_rate: 1.0e-5               # learning rate.
+    gamma: 0.9999                          # scheduler gamma must between(0.0, 1.0) and closer to 1.0 is better.
+
+###########################################################
+#                     TRAINING SETTING                    #
+###########################################################
+max_epoch: 20
+num_snapshots: 5
+
+###########################################################
+#                     OTHER SETTING                       #
+###########################################################
+num_snapshots: 10                 # max number of snapshots to keep while training
+seed: 42                          # random seed for paddle, random, and np.random

examples/other/rhy/data/rhy_predict/rhy_token

@@ -0,0 +1,4 @@
+%
+`
+~
+$

examples/other/rhy/local/data.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+
+aishell_data=$1
+biaobei_data=$2
+processed_path=$3
+
+python3 ./local/pre_for_sp_biaobei.py \
+    --data=${biaobei_data} \
+    --processed_path=${processed_path}
+
+python3 ./local/pre_for_sp_aishell.py \
+    --data=${aishell_data} \
+    --processed_path=${processed_path}
+
+
+echo "Finish data preparation."
+exit 0

examples/other/rhy/local/pre_for_sp_aishell.py

@@ -0,0 +1,50 @@
+import argparse
+import os
+import re
+
+# This is the replacement for rhythm labels to predict.
+# 韵律标签的代替
+replace_ = {"#1": "%", "#2": "`", "#3": "~", "#4": "$"}
+
+
+def replace_rhy_with_punc(line):
+    # r'[：、，；。？！,.:;"?!”’《》【】<=>{}()（）#&@“”^_|…\\]%*$', '', line)     #参考checkcheck_oov.py,
+    line = re.sub(r'[：、，；。？！,.:;"?!’《》【】<=>{}()（）#&@“”^_|…\\]%*$', '', line)
+    for r in replace_.keys():
+        if r in line:
+            line = line.replace(r, replace_[r])
+    return line
+
+
+def pre_and_write(data, file):
+    with open(file, 'a') as rf:
+        for d in data:
+            d = d.split('|')[2].strip()
+            # d = replace_rhy_with_punc(d)
+            d = ' '.join(d) + ' \n'
+            rf.write(d)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Train a FastSpeech2 model.")
+    parser.add_argument("--data", type=str, default="label_train-set.txt")
+    parser.add_argument(
+        "--processed_path", type=str, default="../data/rhy_predict")
+    args = parser.parse_args()
+    os.makedirs(args.processed_path, exist_ok=True)
+
+    with open(args.data) as rf:
+        text = rf.readlines()[5:]
+    len_ = len(text)
+    lens = [int(len_ * 0.9), int(len_ * 0.05), int(len_ * 0.05)]
+    files = ['train.txt', 'test.txt', 'dev.txt']
+
+    i = 0
+    for l_, file in zip(lens, files):
+        file = os.path.join(args.processed_path, file)
+        pre_and_write(text[i:i + l_], file)
+        i = i + l_
+
+
+if __name__ == "__main__":
+    main()

examples/other/rhy/local/pre_for_sp_biaobei.py

@@ -0,0 +1,50 @@
+import argparse
+import os
+import re
+
+replace_ = {"#1": "%", "#2": "`", "#3": "~", "#4": "$"}
+
+
+def replace_rhy_with_punc(line):
+    # r'[：、，；。？！,.:;"?!”’《》【】<=>{}()（）#&@“”^_|…\\]%*$', '', line)     #参考checkcheck_oov.py,
+    line = re.sub(r'^$\*%', '', line)
+    for r in replace_.keys():
+        if r in line:
+            line = line.replace(r, replace_[r])
+    return line
+
+
+def pre_and_write(data, file):
+    with open(file, 'w') as rf:
+        for d in data:
+            d = d.split('\t')[1].strip()
+            d = replace_rhy_with_punc(d)
+            d = ' '.join(d) + ' \n'
+            rf.write(d)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Train a FastSpeech2 model.")
+    parser.add_argument("--data", type=str, default="label_train-set.txt")
+    parser.add_argument(
+        "--processed_path", type=str, default="../data/rhy_predict")
+    args = parser.parse_args()
+    print(args.data, args.processed_path)
+    os.makedirs(args.processed_path, exist_ok=True)
+
+    with open(args.data) as rf:
+        rf = rf.readlines()
+    text = rf[0::2]
+    len_ = len(text)
+    lens = [int(len_ * 0.9), int(len_ * 0.05), int(len_ * 0.05)]
+    files = ['train.txt', 'test.txt', 'dev.txt']
+
+    i = 0
+    for l_, file in zip(lens, files):
+        file = os.path.join(args.processed_path, file)
+        pre_and_write(text[i:i + l_], file)
+        i = i + l_
+
+
+if __name__ == "__main__":
+    main()

examples/other/rhy/local/preprocess.py

@@ -0,0 +1,29 @@
+import argparse
+
+
+def process_sentence(line):
+    if line == '':
+        return ''
+    res = line[0]
+    for i in range(1, len(line)):
+        res += (' ' + line[i])
+    return res
+
+
+if __name__ == "__main__":
+    paser = argparse.ArgumentParser(description="Input filename")
+    paser.add_argument('-input_file')
+    paser.add_argument('-output_file')
+    sentence_cnt = 0
+    args = paser.parse_args()
+    with open(args.input_file, 'r') as f:
+        with open(args.output_file, 'w') as write_f:
+            while True:
+                line = f.readline()
+                if line:
+                    sentence_cnt += 1
+                    write_f.write(process_sentence(line))
+                else:
+                    break
+    print('preprocess over')
+    print('total sentences number:', sentence_cnt)

examples/other/rhy/local/rhy_predict.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+config_path=$1
+train_output_path=$2
+ckpt_name=$3
+text=$4
+ckpt_prefix=${ckpt_name%.*}
+
+python3 ${BIN_DIR}/punc_restore.py \
+    --config=${config_path} \
+    --checkpoint=${train_output_path}/checkpoints/${ckpt_name} \
+    --text=${text}

examples/other/rhy/local/test.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+
+config_path=$1
+train_output_path=$2
+ckpt_name=$3
+
+ckpt_prefix=${ckpt_name%.*}
+
+python3 ${BIN_DIR}/test.py \
+    --config=${config_path} \
+    --checkpoint=${train_output_path}/checkpoints/${ckpt_name}

examples/other/rhy/local/train.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+config_path=$1
+train_output_path=$2
+
+python3 ${BIN_DIR}/train.py \
+    --config=${config_path} \
+    --output-dir=${train_output_path} \
+    --ngpu=1

examples/other/rhy/path.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+export MAIN_ROOT=${PWD}/../../../
+
+export PATH=${MAIN_ROOT}:${MAIN_ROOT}/utils:${PATH}
+export LC_ALL=C
+
+# Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
+export PYTHONIOENCODING=UTF-8
+export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH}
+
+export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/
+
+MODEL=ernie_linear
+export BIN_DIR=${MAIN_ROOT}/paddlespeech/text/exps/${MODEL}

examples/other/rhy/run.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+set -e
+source path.sh
+
+gpus=1
+stage=3
+stop_stage=3
+
+aishell_data=label_train-set.txt
+biaobei_data=000001-010000.txt
+processed_path=data/rhy_predict
+
+conf_path=conf/default.yaml
+train_output_path=exp/rhy
+ckpt_name=snapshot_iter_2600.pdz
+text=我们城市的复苏有赖于他强有力的政策。
+
+# 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
+    ./local/data.sh ${aishell_data} ${biaobei_data} ${processed_path}
+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 ] && [ ${stop_stage} -ge 2 ]; then
+   CUDA_VISIBLE_DEVICES=${gpus} ./local/test.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
+fi
+
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+   CUDA_VISIBLE_DEVICES=${gpus} ./local/rhy_predict.sh ${conf_path} ${train_output_path} ${ckpt_name} ${text}|| exit -1
+fi