HuangLiangJie
3 years ago
committed by
GitHub
commit
e483808c6e
@ -0,0 +1,77 @@
|
||||
# FastSpeech2 with Cantonese language
|
||||
|
||||
## Dataset
|
||||
### Download and Extract
|
||||
If you don't have the Cantonese datasets mentioned above, please download and unzip [Guangzhou_Cantonese_Scripted_Speech_Corpus_Daily_Use_Sentence](https://magichub.com/datasets/guangzhou-cantonese-scripted-speech-corpus-daily-use-sentence/) and [Guangzhou_Cantonese_Scripted_Speech_Corpus_in_Vehicle](https://magichub.com/datasets/guangzhou-cantonese-scripted-speech-corpus-in-the-vehicle/) under `~/datasets/`.
|
||||
|
||||
To obtain better performance, please combine these two datasets together as follows:
|
||||
|
||||
```bash
|
||||
mkdir -p ~/datasets/canton_all/WAV
|
||||
cp -r ~/datasets/Guangzhou_Cantonese_Scripted_Speech_Corpus_Daily_Use_Sentence/WAV/* ~/datasets/canton_all/WAV
|
||||
cp -r ~/datasets/Guangzhou_Cantonese_Scripted_Speech_Corpus_in_Vehicle/WAV/* ~/datasets/canton_all/WAV
|
||||
```
|
||||
|
||||
After that, it should be look like:
|
||||
```
|
||||
~/datasets/canton_all
|
||||
│ └── WAV
|
||||
│ └──G0001
|
||||
│ └──G0002
|
||||
│ ...
|
||||
│ └──G0071
|
||||
│ └──G0072
|
||||
```
|
||||
|
||||
|
||||
### Get MFA Result and Extract
|
||||
We use [MFA1.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for canton_fastspeech2.
|
||||
You can train your MFA model reference to [canton_mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
|
||||
We here provide the MFA results of these two datasets. [canton_alignment.zip](https://paddlespeech.bj.bcebos.com/MFA/Canton/canton_alignment.zip)
|
||||
|
||||
## Get Started
|
||||
Assume the path to the Cantonese MFA result of the two datsets mentioned above is `./canton_alignment`.
|
||||
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 text file.
|
||||
```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, a path of energy features, speaker, and id of each utterance.
|
||||
|
||||
### Training details can refer to the script of [examples/aishell3/tts3](../../aishell3/tts3).
|
||||
|
||||
## Pretrained Model
|
||||
@ -0,0 +1,107 @@
|
||||
###########################################################
|
||||
# FEATURE EXTRACTION SETTING #
|
||||
###########################################################
|
||||
|
||||
fs: 24000 # sr
|
||||
n_fft: 2048 # FFT size (samples).
|
||||
n_shift: 300 # Hop size (samples). 12.5ms
|
||||
win_length: 1200 # Window length (samples). 50ms
|
||||
# If set to null, it will be the same as fft_size.
|
||||
window: "hann" # Window function.
|
||||
|
||||
# Only used for feats_type != raw
|
||||
|
||||
fmin: 80 # Minimum frequency of Mel basis.
|
||||
fmax: 7600 # Maximum frequency of Mel basis.
|
||||
n_mels: 80 # The number of mel basis.
|
||||
|
||||
# Only used for the model using pitch features (e.g. FastSpeech2)
|
||||
# The canton datasets we use are different from others like Databaker or LJSpeech,
|
||||
# we set it to 110 to avoid too many zero-pitch problem.
|
||||
# Reference: https://github.com/JeremyCCHsu/Python-Wrapper-for-World-Vocoder/issues/38
|
||||
f0min: 110 # Minimum f0 for pitch extraction.
|
||||
f0max: 400 # Maximum f0 for pitch extraction.
|
||||
|
||||
|
||||
###########################################################
|
||||
# DATA SETTING #
|
||||
###########################################################
|
||||
batch_size: 32
|
||||
num_workers: 2
|
||||
|
||||
|
||||
###########################################################
|
||||
# MODEL SETTING #
|
||||
###########################################################
|
||||
model:
|
||||
adim: 384 # attention dimension
|
||||
aheads: 2 # number of attention heads
|
||||
elayers: 4 # number of encoder layers
|
||||
eunits: 1536 # number of encoder ff units
|
||||
dlayers: 4 # number of decoder layers
|
||||
dunits: 1536 # number of decoder ff units
|
||||
positionwise_layer_type: conv1d # type of position-wise layer
|
||||
positionwise_conv_kernel_size: 3 # kernel size of position wise conv layer
|
||||
duration_predictor_layers: 2 # number of layers of duration predictor
|
||||
duration_predictor_chans: 256 # number of channels of duration predictor
|
||||
duration_predictor_kernel_size: 3 # filter size of duration predictor
|
||||
postnet_layers: 5 # number of layers of postnset
|
||||
postnet_filts: 5 # filter size of conv layers in postnet
|
||||
postnet_chans: 256 # number of channels of conv layers in postnet
|
||||
use_scaled_pos_enc: True # whether to use scaled positional encoding
|
||||
encoder_normalize_before: True # whether to perform layer normalization before the input
|
||||
decoder_normalize_before: True # whether to perform layer normalization before the input
|
||||
reduction_factor: 1 # reduction factor
|
||||
init_type: xavier_uniform # initialization type
|
||||
init_enc_alpha: 1.0 # initial value of alpha of encoder scaled position encoding
|
||||
init_dec_alpha: 1.0 # initial value of alpha of decoder scaled position encoding
|
||||
transformer_enc_dropout_rate: 0.2 # dropout rate for transformer encoder layer
|
||||
transformer_enc_positional_dropout_rate: 0.2 # dropout rate for transformer encoder positional encoding
|
||||
transformer_enc_attn_dropout_rate: 0.2 # dropout rate for transformer encoder attention layer
|
||||
transformer_dec_dropout_rate: 0.2 # dropout rate for transformer decoder layer
|
||||
transformer_dec_positional_dropout_rate: 0.2 # dropout rate for transformer decoder positional encoding
|
||||
transformer_dec_attn_dropout_rate: 0.2 # dropout rate for transformer decoder attention layer
|
||||
pitch_predictor_layers: 5 # number of conv layers in pitch predictor
|
||||
pitch_predictor_chans: 256 # number of channels of conv layers in pitch predictor
|
||||
pitch_predictor_kernel_size: 5 # kernel size of conv leyers in pitch predictor
|
||||
pitch_predictor_dropout: 0.5 # dropout rate in pitch predictor
|
||||
pitch_embed_kernel_size: 1 # kernel size of conv embedding layer for pitch
|
||||
pitch_embed_dropout: 0.0 # dropout rate after conv embedding layer for pitch
|
||||
stop_gradient_from_pitch_predictor: True # whether to stop the gradient from pitch predictor to encoder
|
||||
energy_predictor_layers: 2 # number of conv layers in energy predictor
|
||||
energy_predictor_chans: 256 # number of channels of conv layers in energy predictor
|
||||
energy_predictor_kernel_size: 3 # kernel size of conv leyers in energy predictor
|
||||
energy_predictor_dropout: 0.5 # dropout rate in energy predictor
|
||||
energy_embed_kernel_size: 1 # kernel size of conv embedding layer for energy
|
||||
energy_embed_dropout: 0.0 # dropout rate after conv embedding layer for energy
|
||||
stop_gradient_from_energy_predictor: False # whether to stop the gradient from energy predictor to encoder
|
||||
spk_embed_dim: 256 # speaker embedding dimension
|
||||
spk_embed_integration_type: concat # speaker embedding integration type
|
||||
|
||||
|
||||
|
||||
###########################################################
|
||||
# UPDATER SETTING #
|
||||
###########################################################
|
||||
updater:
|
||||
use_masking: True # whether to apply masking for padded part in loss calculation
|
||||
|
||||
|
||||
###########################################################
|
||||
# OPTIMIZER SETTING #
|
||||
###########################################################
|
||||
optimizer:
|
||||
optim: adam # optimizer type
|
||||
learning_rate: 0.001 # learning rate
|
||||
|
||||
###########################################################
|
||||
# TRAINING SETTING #
|
||||
###########################################################
|
||||
max_epoch: 1000
|
||||
num_snapshots: 5
|
||||
|
||||
|
||||
###########################################################
|
||||
# OTHER SETTING #
|
||||
###########################################################
|
||||
seed: 10086
|
||||
@ -0,0 +1,75 @@
|
||||
#!/bin/bash
|
||||
|
||||
stage=0
|
||||
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 ${MAIN_ROOT}/utils/gen_duration_from_textgrid.py \
|
||||
--inputdir=./canton_alignment \
|
||||
--output durations.txt \
|
||||
--config=${config_path}
|
||||
fi
|
||||
|
||||
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
|
||||
# extract features
|
||||
echo "Extract features ..."
|
||||
python3 ${BIN_DIR}/preprocess.py \
|
||||
--dataset=canton \
|
||||
--rootdir=~/datasets/canton_all \
|
||||
--dumpdir=dump \
|
||||
--dur-file=durations.txt \
|
||||
--config=${config_path} \
|
||||
--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"
|
||||
|
||||
python3 ${MAIN_ROOT}/utils/compute_statistics.py \
|
||||
--metadata=dump/train/raw/metadata.jsonl \
|
||||
--field-name="pitch"
|
||||
|
||||
python3 ${MAIN_ROOT}/utils/compute_statistics.py \
|
||||
--metadata=dump/train/raw/metadata.jsonl \
|
||||
--field-name="energy"
|
||||
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 ${BIN_DIR}/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
|
||||
|
||||
python3 ${BIN_DIR}/normalize.py \
|
||||
--metadata=dump/dev/raw/metadata.jsonl \
|
||||
--dumpdir=dump/dev/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
|
||||
|
||||
python3 ${BIN_DIR}/normalize.py \
|
||||
--metadata=dump/test/raw/metadata.jsonl \
|
||||
--dumpdir=dump/test/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
|
||||
@ -0,0 +1 @@
|
||||
../../../aishell3/tts3/local/synthesize.sh
|
||||
@ -0,0 +1,53 @@
|
||||
#!/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 ${BIN_DIR}/../synthesize_e2e.py \
|
||||
--am=fastspeech2_canton \
|
||||
--am_config=${config_path} \
|
||||
--am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
|
||||
--am_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 \
|
||||
--lang=canton \
|
||||
--text=${BIN_DIR}/../sentences_canton.txt \
|
||||
--output_dir=${train_output_path}/test_e2e \
|
||||
--phones_dict=dump/phone_id_map.txt \
|
||||
--speaker_dict=dump/speaker_id_map.txt \
|
||||
--spk_id=0 \
|
||||
--inference_dir=${train_output_path}/inference
|
||||
fi
|
||||
|
||||
# hifigan
|
||||
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
|
||||
echo "in hifigan syn_e2e"
|
||||
FLAGS_allocator_strategy=naive_best_fit \
|
||||
FLAGS_fraction_of_gpu_memory_to_use=0.01 \
|
||||
python3 ${BIN_DIR}/../synthesize_e2e.py \
|
||||
--am=fastspeech2_canton \
|
||||
--am_config=${config_path} \
|
||||
--am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
|
||||
--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.pdz \
|
||||
--voc_stat=hifigan_aishell3_ckpt_0.2.0/feats_stats.npy \
|
||||
--lang=canton \
|
||||
--text=${BIN_DIR}/../sentences_canton.txt \
|
||||
--output_dir=${train_output_path}/test_e2e \
|
||||
--phones_dict=dump/phone_id_map.txt \
|
||||
--speaker_dict=dump/speaker_id_map.txt \
|
||||
--spk_id=0 \
|
||||
--inference_dir=${train_output_path}/inference
|
||||
fi
|
||||
@ -0,0 +1 @@
|
||||
../../../aishell3/tts3/local/train.sh
|
||||
@ -0,0 +1 @@
|
||||
../../csmsc/tts3/path.sh
|
||||
@ -0,0 +1,38 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -e
|
||||
source path.sh
|
||||
|
||||
gpus=0
|
||||
stage=0
|
||||
stop_stage=100
|
||||
|
||||
conf_path=conf/default.yaml
|
||||
train_output_path=exp/default
|
||||
|
||||
ckpt_name=snapshot_iter_280000.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
|
||||
./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
|
||||
@ -0,0 +1,7 @@
|
||||
001 白云山爬过一次嘅，好远啊，爬上去都成两个钟
|
||||
002 睇书咯，番屋企，而家好多人好少睇书噶喎
|
||||
003 因为如果唔考试嘅话，工资好低噶
|
||||
004 冇固定噶，你中意休边日就边日噶
|
||||
005 即系太迟嘅话咧，落班太迟嘅话就喺出边食啲咯
|
||||
006 是非有公理，慎言莫冒犯别人
|
||||
007 遇上冷风雨，休太认真
|
||||
@ -0,0 +1,106 @@
|
||||
# Copyright (c) 2021 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 typing import Dict
|
||||
from typing import List
|
||||
|
||||
import numpy as np
|
||||
import paddle
|
||||
import ToJyutping
|
||||
|
||||
from paddlespeech.t2s.frontend.zh_normalization.text_normlization import TextNormalizer
|
||||
|
||||
INITIALS = [
|
||||
'p', 'b', 't', 'd', 'ts', 'dz', 'k', 'g', 'kw', 'gw', 'f', 'h', 'l', 'm',
|
||||
'ng', 'n', 's', 'y', 'w', 'c', 'z', 'j'
|
||||
]
|
||||
INITIALS += ['sp', 'spl', 'spn', 'sil']
|
||||
|
||||
|
||||
def get_lines(cantons: List[str]):
|
||||
phones = []
|
||||
for canton in cantons:
|
||||
for consonant in INITIALS:
|
||||
if canton.startswith(consonant):
|
||||
c, v = canton[:len(consonant)], canton[len(consonant):]
|
||||
phones = phones + [c, v]
|
||||
return phones
|
||||
|
||||
|
||||
class CantonFrontend():
|
||||
def __init__(self, phone_vocab_path: str):
|
||||
self.text_normalizer = TextNormalizer()
|
||||
self.punc = "：，；。？！“”‘’':,;.?!"
|
||||
|
||||
self.vocab_phones = {}
|
||||
if phone_vocab_path:
|
||||
with open(phone_vocab_path, 'rt', encoding='utf-8') as f:
|
||||
phn_id = [line.strip().split() for line in f.readlines()]
|
||||
for phn, id in phn_id:
|
||||
self.vocab_phones[phn] = int(id)
|
||||
|
||||
# if merge_sentences, merge all sentences into one phone sequence
|
||||
def _g2p(self, sentences: List[str],
|
||||
merge_sentences: bool=True) -> List[List[str]]:
|
||||
phones_list = []
|
||||
for sentence in sentences:
|
||||
phones_str = ToJyutping.get_jyutping_text(sentence)
|
||||
phones_split = get_lines(phones_str.split(' '))
|
||||
phones_list.append(phones_split)
|
||||
return phones_list
|
||||
|
||||
def _p2id(self, phonemes: List[str]) -> np.ndarray:
|
||||
# replace unk phone with sp
|
||||
phonemes = [
|
||||
phn if phn in self.vocab_phones else "sp" for phn in phonemes
|
||||
]
|
||||
phone_ids = [self.vocab_phones[item] for item in phonemes]
|
||||
return np.array(phone_ids, np.int64)
|
||||
|
||||
def get_phonemes(self,
|
||||
sentence: str,
|
||||
merge_sentences: bool=True,
|
||||
print_info: bool=False) -> List[List[str]]:
|
||||
sentences = self.text_normalizer.normalize(sentence)
|
||||
phonemes = self._g2p(sentences, merge_sentences=merge_sentences)
|
||||
if print_info:
|
||||
print("----------------------------")
|
||||
print("text norm results:")
|
||||
print(sentences)
|
||||
print("----------------------------")
|
||||
print("g2p results:")
|
||||
print(phonemes)
|
||||
print("----------------------------")
|
||||
return phonemes
|
||||
|
||||
def get_input_ids(self,
|
||||
sentence: str,
|
||||
merge_sentences: bool=True,
|
||||
print_info: bool=False,
|
||||
to_tensor: bool=True) -> Dict[str, List[paddle.Tensor]]:
|
||||
|
||||
phonemes = self.get_phonemes(
|
||||
sentence, merge_sentences=merge_sentences, print_info=print_info)
|
||||
result = {}
|
||||
temp_phone_ids = []
|
||||
|
||||
for phones in phonemes:
|
||||
if phones:
|
||||
phone_ids = self._p2id(phones)
|
||||
# if use paddle.to_tensor() in onnxruntime, the first time will be too low
|
||||
if to_tensor:
|
||||
phone_ids = paddle.to_tensor(phone_ids)
|
||||
temp_phone_ids.append(phone_ids)
|
||||
if temp_phone_ids:
|
||||
result["phone_ids"] = temp_phone_ids
|
||||
return result
|
||||
Loading…
Reference in new issue