新网杯topline：手把手教你构建中文语音合成模型

git clone https://github.com/PaddlePaddle/Parakeet
 cd Parakeet 
pip install -e 。

sudo apt-get installlibsndfile1

import nltk
nltk.download("punkt")
nltk.download("cmudict")
[nltk_data] Downloading package punkt to /home/aistudio/nltk_data...
[nltk_data]   Package punkt is already up-to-date!
[nltk_data] Downloading package cmudict to /home/aistudio/nltk_data...
[nltk_data]   Package cmudict is already up-to-date!

!unzip data/data117129/BZNSYP.zip > /dev/null 2>&1

#!/bin/bash
stage=0
stop_stage=100
# export MAIN_ROOT=`realpath ${PWD}/../../../`
export MAIN_ROOT=./
echo $MAIN_ROOT
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=conf/default.yaml
fi
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
    # extract features
    echo "Extract features ..."
    python3 ./preprocess.py \
        --dataset=baker \
        --rootdir=~/BZNSYP/ \
        --dumpdir=dump \
        --dur-file=durations.txt \
        --config=conf/default.yaml \
        --num-cpu=20 \
        --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/speaker to id, dev and test should use train's stats
    echo "Normalize ..."
    python3 ./normalize.py \
        --metadata=dump/train/raw/metadata.jsonl \
        --dumpdir=dump/train/norm \
        --speech-stats=dump/train/speech_stats.npy \
        --pitch-stats=dump/train/pitch_stats.npy \
        --energy-stats=dump/train/energy_stats.npy \
        --phones-dict=dump/phone_id_map.txt \
        --speaker-dict=dump/speaker_id_map.txt
fi

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

usage: train.py [-h] [--config CONFIG] [--train-metadata TRAIN_METADATA]
                [--dev-metadata DEV_METADATA] [--output-dir OUTPUT_DIR]
                [--device DEVICE] [--nprocs NPROCS] [--verbose VERBOSE]
                [--phones-dict PHONES_DICT] [--speaker-dict SPEAKER_DICT]
Train a FastSpeech2 model.
optional arguments:
  -h, --help            show this help message and exit
  --config CONFIG       fastspeech2 config file.
  --train-metadata TRAIN_METADATA
                        training data.
  --dev-metadata DEV_METADATA
                        dev data.
  --output-dir OUTPUT_DIR
                        output dir.
  --device DEVICE       device type to use.
  --nprocs NPROCS       number of processes.
  --verbose VERBOSE     verbose.
  --phones-dict PHONES_DICT
                        phone vocabulary file.
  --speaker-dict SPEAKER_DICT
                        speaker id map file for multiple speaker model.

usage: synthesize.py [-h] [--fastspeech2-config FASTSPEECH2_CONFIG]
                     [--fastspeech2-checkpoint FASTSPEECH2_CHECKPOINT]
                     [--fastspeech2-stat FASTSPEECH2_STAT]
                     [--pwg-config PWG_CONFIG]
                     [--pwg-checkpoint PWG_CHECKPOINT] [--pwg-stat PWG_STAT]
                     [--phones-dict PHONES_DICT] [--speaker-dict SPEAKER_DICT]
                     [--test-metadata TEST_METADATA] [--output-dir OUTPUT_DIR]
                     [--device DEVICE] [--verbose VERBOSE]

FLAGS_allocator_strategy=naive_best_fit
FLAGS_fraction_of_gpu_memory_to_use=0.01
python3 synthesize_e2e.py
--fastspeech2-config=fastspeech2_nosil_baker_ckpt_0.4/default.yaml
--fastspeech2-checkpoint=fastspeech2_nosil_baker_ckpt_0.4/snapshot_iter_76000.pdz
--fastspeech2-stat=fastspeech2_nosil_baker_ckpt_0.4/speech_stats.npy
--pwg-config=pwg_baker_ckpt_0.4/pwg_default.yaml
--pwg-checkpoint=pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz
--pwg-stat=pwg_baker_ckpt_0.4/pwg_stats.npy
--text=../sentences.txt
--output-dir=exp/default/test_e2e
--device="gpu"
--phones-dict=fastspeech2_nosil_baker_ckpt_0.4/phone_id_map.txt

# #!/bin/bash
# %cd exp/default/
# !for x in ./test_e2e/*.wav
# !do 
# !  b=${x##*/}
# !  sox ./test_e2e/$b -r 16000 ./致Great/$b
# !done
!sed -i 's/\r$//' ./xw_predict.sh
!chmod +x ./xw_predict.sh
!./xw_predict.sh