[TTS] add opencpop PWGAN example

examples/opencpop/voc1/README.md

@@ -0,0 +1,139 @@
+# Parallel WaveGAN with Opencpop
+This example contains code used to train a [parallel wavegan](http://arxiv.org/abs/1910.11480) model with [Mandarin singing corpus](https://wenet.org.cn/opencpop/).
+
+## Dataset
+### Download and Extract
+Download Opencpop from it's [Official Website](https://wenet.org.cn/opencpop/download/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/Opencpop`.
+
+## Get Started
+Assume the path to the dataset is `~/datasets/Opencpop`.
+Run the command below to
+1. **source path**.
+2. preprocess the dataset.
+3. train the model.
+4. synthesize wavs.
+    - synthesize waveform from `metadata.jsonl`.
+```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 ${conf_path}
+```
+When it is done. A `dump` folder is created in the current directory. The structure of the dump folder is listed below.
+
+```text
+dump
+├── dev
+│   ├── norm
+│   └── raw
+├── test
+│   ├── norm
+│   └── raw
+└── train
+    ├── norm
+    ├── raw
+    └── feats_stats.npy
+```
+The dataset is split into 3 parts, namely `train`, `dev`, and `test`, each of which contains a `norm` and `raw` subfolder. The `raw` folder contains the log magnitude of the mel spectrogram of each utterance, while the norm folder contains the normalized spectrogram. The statistics used to normalize the spectrogram are computed from the training set, which is located in `dump/train/feats_stats.npy`.
+
+Also, there is a `metadata.jsonl` in each subfolder. It is a table-like file that contains id and paths to the spectrogram of each utterance.
+
+### Model Training
+```bash
+CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${train_output_path}
+```
+`./local/train.sh` calls `${BIN_DIR}/train.py`.
+Here's the complete help message.
+
+```text
+usage: train.py [-h] [--config CONFIG] [--train-metadata TRAIN_METADATA]
+                [--dev-metadata DEV_METADATA] [--output-dir OUTPUT_DIR]
+                [--ngpu NGPU] [--batch-size BATCH_SIZE] [--max-iter MAX_ITER]
+                [--run-benchmark RUN_BENCHMARK]
+                [--profiler_options PROFILER_OPTIONS]
+
+Train a ParallelWaveGAN model.
+
+optional arguments:
+  -h, --help            show this help message and exit
+  --config CONFIG       ParallelWaveGAN config file.
+  --train-metadata TRAIN_METADATA
+                        training data.
+  --dev-metadata DEV_METADATA
+                        dev data.
+  --output-dir OUTPUT_DIR
+                        output dir.
+  --ngpu NGPU           if ngpu == 0, use cpu.
+
+benchmark:
+  arguments related to benchmark.
+
+  --batch-size BATCH_SIZE
+                        batch size.
+  --max-iter MAX_ITER   train max steps.
+  --run-benchmark RUN_BENCHMARK
+                        runing benchmark or not, if True, use the --batch-size
+                        and --max-iter.
+  --profiler_options PROFILER_OPTIONS
+                        The option of profiler, which should be in format
+                        "key1=value1;key2=value2;key3=value3".
+```
+
+1. `--config` is a config file in yaml format to overwrite the default config, which can be found at `conf/default.yaml`.
+2. `--train-metadata` and `--dev-metadata` should be the metadata file in the normalized subfolder of `train` and `dev` in the `dump` folder.
+3. `--output-dir` is the directory to save the results of the experiment. Checkpoints are saved in `checkpoints/` inside this directory.
+4. `--ngpu` is the number of gpus to use, if ngpu == 0, use cpu.
+
+### Synthesizing
+`./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`.
+```bash
+CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name}
+```
+```text
+usage: synthesize.py [-h] [--generator-type GENERATOR_TYPE] [--config CONFIG]
+                     [--checkpoint CHECKPOINT] [--test-metadata TEST_METADATA]
+                     [--output-dir OUTPUT_DIR] [--ngpu NGPU]
+
+Synthesize with GANVocoder.
+
+optional arguments:
+  -h, --help            show this help message and exit
+  --generator-type GENERATOR_TYPE
+                        type of GANVocoder, should in {pwgan, mb_melgan,
+                        style_melgan, } now
+  --config CONFIG       GANVocoder config file.
+  --checkpoint CHECKPOINT
+                        snapshot to load.
+  --test-metadata TEST_METADATA
+                        dev data.
+  --output-dir OUTPUT_DIR
+                        output dir.
+  --ngpu NGPU           if ngpu == 0, use cpu.
+```
+
+1. `--config` parallel wavegan config file. You should use the same config with which the model is trained.
+2. `--checkpoint` is the checkpoint to load. Pick one of the checkpoints from `checkpoints` inside the training output directory.
+3. `--test-metadata` is the metadata of the test dataset. Use the `metadata.jsonl` in the `dev/norm` subfolder from the processed directory.
+4. `--output-dir` is the directory to save the synthesized audio files.
+5. `--ngpu` is the number of gpus to use, if ngpu == 0, use cpu.
+
+## Pretrained Models
+The pretrained model can be downloaded here:
+- [pwgan_opencpop_ckpt_1.4.0](https://paddlespeech.bj.bcebos.com/t2s/svs/opencpop/pwgan_opencpop_ckpt_1.4.0.zip)
+
+
+Parallel WaveGAN checkpoint contains files listed below.
+
+```text
+pwgan_opencpop_ckpt_1.4.0
+├── default.yaml                    # default config used to train parallel wavegan
+├── snapshot_iter_100000.pdz        # generator parameters of parallel wavegan
+└── feats_stats.npy                 # statistics used to normalize spectrogram when training parallel wavegan
+```
+## Acknowledgement
+We adapted some code from https://github.com/kan-bayashi/ParallelWaveGAN.

examples/opencpop/voc1/conf/default.yaml

@@ -0,0 +1,119 @@
+# This is the hyperparameter configuration file for Parallel WaveGAN.
+# Please make sure this is adjusted for the CSMSC dataset. If you want to
+# apply to the other dataset, you might need to carefully change some parameters.
+# This configuration requires 12 GB GPU memory and takes ~3 days on RTX TITAN.
+
+###########################################################
+#                FEATURE EXTRACTION SETTING               #
+###########################################################
+fs: 24000                # Sampling rate.
+n_fft: 512              # FFT size (samples).
+n_shift: 128             # Hop size (samples). 12.5ms
+win_length: 512         # Window length (samples). 50ms
+                         # If set to null, it will be the same as fft_size.
+window: "hann"           # Window function.
+n_mels: 80               # Number of mel basis.
+fmin: 30                 # Minimum freq in mel basis calculation. (Hz)
+fmax: 12000               # Maximum frequency in mel basis calculation. (Hz)
+
+
+###########################################################
+#         GENERATOR NETWORK ARCHITECTURE SETTING          #
+###########################################################
+generator_params:
+    in_channels: 1        # Number of input channels.
+    out_channels: 1       # Number of output channels.
+    kernel_size: 3        # Kernel size of dilated convolution.
+    layers: 30            # Number of residual block layers.
+    stacks: 3             # Number of stacks i.e., dilation cycles.
+    residual_channels: 64 # Number of channels in residual conv.
+    gate_channels: 128    # Number of channels in gated conv.
+    skip_channels: 64     # Number of channels in skip conv.
+    aux_channels: 80      # Number of channels for auxiliary feature conv.
+                          # Must be the same as num_mels.
+    aux_context_window: 2 # Context window size for auxiliary feature.
+                          # If set to 2, previous 2 and future 2 frames will be considered.
+    dropout: 0.0          # Dropout rate. 0.0 means no dropout applied.
+    bias: True            # use bias in residual blocks
+    use_weight_norm: True # Whether to use weight norm.
+                          # If set to true, it will be applied to all of the conv layers.
+    use_causal_conv: False               # use causal conv in residual blocks and upsample layers
+    upsample_scales: [8, 4, 2, 2]     # Upsampling scales. Prodcut of these must be the same as hop size.
+    interpolate_mode: "nearest" # upsample net interpolate mode
+    freq_axis_kernel_size: 1 # upsamling net: convolution kernel size in frequencey axis
+    nonlinear_activation: null
+    nonlinear_activation_params: {}
+
+###########################################################
+#       DISCRIMINATOR NETWORK ARCHITECTURE SETTING        #
+###########################################################
+discriminator_params:
+    in_channels: 1        # Number of input channels.
+    out_channels: 1       # Number of output channels.
+    kernel_size: 3        # Number of output channels.
+    layers: 10            # Number of conv layers.
+    conv_channels: 64     # Number of chnn layers.
+    bias: True            # Whether to use bias parameter in conv.
+    use_weight_norm: True # Whether to use weight norm.
+                          # If set to true, it will be applied to all of the conv layers.
+    nonlinear_activation: "leakyrelu" # Nonlinear function after each conv.
+    nonlinear_activation_params:      # Nonlinear function parameters
+        negative_slope: 0.2           # Alpha in leakyrelu.
+
+###########################################################
+#                   STFT LOSS SETTING                     #
+###########################################################
+stft_loss_params:
+    fft_sizes: [1024, 2048, 512]  # List of FFT size for STFT-based loss.
+    hop_sizes: [120, 240, 50]     # List of hop size for STFT-based loss
+    win_lengths: [600, 1200, 240] # List of window length for STFT-based loss.
+    window: "hann"         # Window function for STFT-based loss
+
+###########################################################
+#               ADVERSARIAL LOSS SETTING                  #
+###########################################################
+lambda_adv: 4.0  # Loss balancing coefficient.
+
+###########################################################
+#                  DATA LOADER SETTING                    #
+###########################################################
+batch_size: 8              # Batch size.
+batch_max_steps: 25500     # Length of each audio in batch. Make sure dividable by n_shift.
+num_workers: 1             # Number of workers in DataLoader.
+
+###########################################################
+#             OPTIMIZER & SCHEDULER SETTING               #
+###########################################################
+generator_optimizer_params:
+    epsilon: 1.0e-6        # Generator's epsilon.
+    weight_decay: 0.0      # Generator's weight decay coefficient.
+generator_scheduler_params:
+    learning_rate: 0.0001  # Generator's learning rate.
+    step_size: 200000      # Generator's scheduler step size.
+    gamma: 0.5             # Generator's scheduler gamma.
+                           # At each step size, lr will be multiplied by this parameter.
+generator_grad_norm: 10    # Generator's gradient norm.
+discriminator_optimizer_params:
+    epsilon: 1.0e-6            # Discriminator's epsilon.
+    weight_decay: 0.0          # Discriminator's weight decay coefficient.
+discriminator_scheduler_params:
+    learning_rate: 0.00005     # Discriminator's learning rate.
+    step_size: 200000          # Discriminator's scheduler step size.
+    gamma: 0.5                 # Discriminator's scheduler gamma.
+                               # At each step size, lr will be multiplied by this parameter.
+discriminator_grad_norm: 1     # Discriminator's gradient norm.
+
+###########################################################
+#                    INTERVAL SETTING                     #
+###########################################################
+discriminator_train_start_steps: 100000 # Number of steps to start to train discriminator.
+train_max_steps: 400000                 # Number of training steps.
+save_interval_steps: 5000               # Interval steps to save checkpoint.
+eval_interval_steps: 1000               # Interval steps to evaluate the network.
+
+###########################################################
+#                     OTHER SETTING                       #
+###########################################################
+num_save_intermediate_results: 4  # Number of results to be saved as intermediate results.
+num_snapshots: 10                 # max number of snapshots to keep while training
+seed: 42                          # random seed for paddle, random, and np.random

examples/opencpop/voc1/local/PTQ_static.sh

@@ -0,0 +1 @@
+../../../csmsc/voc1/local/PTQ_static.sh

examples/opencpop/voc1/local/dygraph_to_static.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+config_path=$1
+train_output_path=$2
+ckpt_name=$3
+
+FLAGS_allocator_strategy=naive_best_fit \
+FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+python3 ${BIN_DIR}/../../dygraph_to_static.py \
+    --type=voc \
+    --voc=pwgan_opencpop \
+    --voc_config=${config_path} \
+    --voc_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+    --voc_stat=dump/train/feats_stats.npy \
+    --inference_dir=exp/default/inference/

examples/opencpop/voc1/local/preprocess.sh

@@ -0,0 +1,47 @@
+#!/bin/bash
+
+stage=0
+stop_stage=100
+
+config_path=$1
+
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    # extract features
+    echo "Extract features ..."
+    python3 ${BIN_DIR}/../preprocess.py \
+        --rootdir=~/datasets/Opencpop/segments/ \
+        --dataset=opencpop \
+        --dumpdir=dump \
+        --dur-file=~/datasets/Opencpop/segments/transcriptions.txt \
+        --config=${config_path} \
+        --cut-sil=False \
+        --num-cpu=20
+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="feats"
+fi
+
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+    # normalize, 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 \
+        --stats=dump/train/feats_stats.npy
+    python3 ${BIN_DIR}/../normalize.py \
+        --metadata=dump/dev/raw/metadata.jsonl \
+        --dumpdir=dump/dev/norm \
+        --stats=dump/train/feats_stats.npy
+
+    python3 ${BIN_DIR}/../normalize.py \
+        --metadata=dump/test/raw/metadata.jsonl \
+        --dumpdir=dump/test/norm \
+        --stats=dump/train/feats_stats.npy
+fi

examples/opencpop/voc1/local/synthesize.sh

@@ -0,0 +1 @@
+../../../csmsc/voc1/local/synthesize.sh

examples/opencpop/voc1/local/train.sh

@@ -0,0 +1 @@
+../../../csmsc/voc1/local/train.sh

examples/opencpop/voc1/path.sh

@@ -0,0 +1 @@
+../../csmsc/voc1/path.sh

examples/opencpop/voc1/run.sh

@@ -0,0 +1,42 @@
+#!/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_100000.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 ] && [ ${stop_stage} -ge 2 ]; then
+    # synthesize
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
+fi
+
+# dygraph to static
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/dygraph_to_static.sh  ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
+fi
+
+# PTQ_static
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/PTQ_static.sh  ${train_output_path} pwgan_opencpop || exit -1
+fi

paddlespeech/t2s/exps/PTQ_static.py

@@ -42,6 +42,7 @@ def parse_args():
             'hifigan_aishell3',
             'hifigan_ljspeech',
             'hifigan_vctk',
+            'pwgan_opencpop',
         ],
         help='Choose model type of tts task.')