Merge pull request #73 from PaddlePaddle/develop

add README for transformer_tts, waveflow and wavenet

examples/tacotron2/README.md

@@ -0,0 +1,77 @@
+# Tacotron2
+
+PaddlePaddle dynamic graph implementation of Tacotron2, a neural network architecture for speech synthesis directly from text. The implementation is based on [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://arxiv.org/abs/1712.05884).
+
+## Project Structure
+
+```text
+├── config.py              # default configuration file
+├── ljspeech.py            # dataset and dataloader settings for LJSpeech
+├── preprocess.py          # script to preprocess LJSpeech dataset
+├── synthesis.py           # script to synthesize spectrogram from text
+├── train.py               # script for tacotron2 model training
+```
+
+## Dataset
+
+We experiment with the LJSpeech dataset. Download and unzip [LJSpeech](https://keithito.com/LJ-Speech-Dataset/).
+
+```bash
+wget https://data.keithito.com/data/speech/LJSpeech-1.1.tar.bz2
+tar xjvf LJSpeech-1.1.tar.bz2
+```
+
+Then you need to preprocess the data by running ``preprocess.py``, the preprocessed data will be placed in ``--output`` directory.
+
+```bash
+python preprocess.py \
+--input=${DATAPATH} \
+--output=${PREPROCESSEDDATAPATH} \
+-v  \
+```
+
+For more help on arguments
+
+``python preprocess.py --help``.
+
+## Train the model
+
+Tacotron2 model can be trained by running ``train.py``.
+
+```bash
+python train.py \
+--data=${PREPROCESSEDDATAPATH} \
+--output=${OUTPUTPATH} \
+--device=gpu \
+```
+
+If you want to train on CPU, just set ``--device=cpu``.
+If you want to train on multiple GPUs, just set ``--nprocs`` as num of GPU.
+By default, training will be resumed from the latest checkpoint in ``--output``, if you want to start a new training, please use a new ``${OUTPUTPATH}`` with no checkpoint. And if you want to resume from an other existing model, you should set ``checkpoint_path`` to be the checkpoint path you want to load.
+
+**Note: The checkpoint path cannot contain the file extension.**
+
+For more help on arguments
+
+``python train_transformer.py --help``.
+
+## Synthesis
+
+After training the Tacotron2, spectrogram can be synthesized by running ``synthesis.py``.
+
+```bash
+python synthesis.py \
+--config=${CONFIGPATH} \
+--checkpoint_path=${CHECKPOINTPATH} \
+--input=${TEXTPATH} \
+--output=${OUTPUTPATH}
+--device=gpu
+```
+
+The ``${CONFIGPATH}`` needs to be matched with ``${CHECKPOINTPATH}``.
+
+For more help on arguments
+
+``python synthesis.py --help``.
+
+Then you can find the spectrogram files in ``${OUTPUTPATH}``, and then they can be the input of vocoder like [waveflow](../waveflow/README.md#Synthesis) to get audio files.

examples/transformer_tts/README.md

@@ -0,0 +1,48 @@
+# TransformerTTS with LJSpeech
+
+## Dataset
+
+### Download the datasaet.
+
+```bash
+wget https://data.keithito.com/data/speech/LJSpeech-1.1.tar.bz2
+```
+
+### Extract the dataset.
+
+```bash
+tar xjvf LJSpeech-1.1.tar.bz2
+```
+
+### Preprocess the dataset. 
+
+Assume the path to save the preprocessed dataset is `ljspeech_transformer_tts`. Run the command below to preprocess the dataset.
+
+```bash
+python preprocess.py --input=LJSpeech-1.1/  --output=ljspeech_transformer_tts
+```
+
+## Train the model
+
+The training script requires 4 command line arguments.
+`--data` is the path of the training dataset, `--output` is the path of the output direcctory (we recommend to use a subdirectory in `runs` to manage different experiments.)
+
+`--device` should be "cpu" or "gpu", `--nprocs` is the number of processes to train the model in parallel.
+
+```bash
+python train.py --data=ljspeech_transformer_tts/ --output=runs/test --device="gpu" --nprocs=1
+```
+
+If you want distributed training, set a larger `--nprocs` (e.g. 4). Note that distributed training with cpu is not supported yet.
+
+## Synthesize
+
+Synthesize waveform. We assume the `--input` is a text file, one sentence per line, and `--output` is a directory to save the synthesized mel spectrogram(log magnitude) in `.npy` format. The mel spectrograms can be used with `Waveflow` to generate waveforms.
+
+`--checkpoint_path` should be the path of the parameter file (`.pdparams`) to load. Note that the extention name `.pdparmas` is not included here.
+
+`--device` specifies to device to run synthesis on.
+
+```bash
+python synthesize.py --input=sentence.txt --output=mels/ --checkpoint_path='step-310000' --device="gpu" --verbose
+```

examples/waveflow/README.md

@@ -0,0 +1,48 @@
+# WaveFlow with LJSpeech
+
+## Dataset
+
+### Download the datasaet.
+
+```bash
+wget https://data.keithito.com/data/speech/LJSpeech-1.1.tar.bz2
+```
+
+### Extract the dataset.
+
+```bash
+tar xjvf LJSpeech-1.1.tar.bz2
+```
+
+### Preprocess the dataset. 
+
+Assume the path to save the preprocessed dataset is `ljspeech_waveflow`. Run the command below to preprocess the dataset.
+
+```bash
+python preprocess.py --input=LJSpeech-1.1/  --output=ljspeech_waveflow
+```
+
+## Train the model
+
+The training script requires 4 command line arguments.
+`--data` is the path of the training dataset, `--output` is the path of the output directory (we recommend to use a subdirectory in `runs` to manage different experiments.)
+
+`--device` should be "cpu" or "gpu", `--nprocs` is the number of processes to train the model in parallel.
+
+```bash
+python train.py --data=ljspeech_waveflow/ --output=runs/test --device="gpu" --nprocs=1
+```
+
+If you want distributed training, set a larger `--nprocs` (e.g. 4). Note that distributed training with cpu is not supported yet.
+
+## Synthesize
+
+Synthesize waveform. We assume the `--input` is a directory containing several mel spectrograms(log magnitude) in `.npy` format. The output would be saved in `--output` directory, containing several `.wav` files, each with the same name as the mel spectrogram does.
+
+`--checkpoint_path` should be the path of the parameter file (`.pdparams`) to load. Note that the extention name `.pdparmas` is not included here.
+
+`--device` specifies to device to run synthesis on.
+
+```bash
+python synthesize.py --input=mels/ --output=wavs/ --checkpoint_path='step-2000000' --device="gpu" --verbose
+```

examples/wavenet/README.md

@@ -0,0 +1,48 @@
+# WaveNet with LJSpeech
+
+## Dataset
+
+### Download the datasaet.
+
+```bash
+wget https://data.keithito.com/data/speech/LJSpeech-1.1.tar.bz2
+```
+
+### Extract the dataset.
+
+```bash
+tar xjvf LJSpeech-1.1.tar.bz2
+```
+
+### Preprocess the dataset. 
+
+Assume the path to save the preprocessed dataset is `ljspeech_wavenet`. Run the command below to preprocess the dataset.
+
+```bash
+python preprocess.py --input=LJSpeech-1.1/  --output=ljspeech_wavenet
+```
+
+## Train the model
+
+The training script requires 4 command line arguments.
+`--data` is the path of the training dataset, `--output` is the path of the output directory (we recommend to use a subdirectory in `runs` to manage different experiments.)
+
+`--device` should be "cpu" or "gpu", `--nprocs` is the number of processes to train the model in parallel.
+
+```bash
+python train.py --data=ljspeech_wavenet/ --output=runs/test --device="gpu" --nprocs=1
+```
+
+If you want distributed training, set a larger `--nprocs` (e.g. 4). Note that distributed training with cpu is not supported yet.
+
+## Synthesize
+
+Synthesize waveform. We assume the `--input` is a directory containing several mel spectrograms(normalized into range[0, 1)) in `.npy` format. The output would be saved in `--output` directory, containing several `.wav` files, each with the same name as the mel spectrogram does.
+
+`--checkpoint_path` should be the path of the parameter file (`.pdparams`) to load. Note that the extention name `.pdparmas` is not included here.
+
+`--device` specifies to device to run synthesis on. Due to the autoregressiveness of wavenet, using cpu may be faster.
+
+```bash
+python synthesize.py --input=mels/ --output=wavs/ --checkpoint_path='step-2450000' --device="cpu" --verbose
+```