[한국어 가이드]
TensorFlow implementation of:
- Deep Voice 2: Multi-Speaker Neural Text-to-Speech
- Listening while Speaking: Speech Chain by Deep Learning
- Tacotron: Towards End-to-End Speech Synthesis
Samples audios (in Korean) can be found here.
- Python 3.6+
- FFmpeg
- Tensorflow 1.3
After preparing Tensorflow, install prerequisites with:
pip3 install -r requirements.txt
python -c "import nltk; nltk.download('punkt')"
If you want to synthesize a speech in Korean dicrectly, follow 2-3. Download pre-trained models.
The datasets
directory should look like:
datasets
├── jtbc
│ ├── alignment.json
│ └── audio
│ ├── 1.mp3
│ ├── 2.mp3
│ ├── 3.mp3
│ └── ...
└── YOUR_DATASET
├── alignment.json
└── audio
├── 1.mp3
├── 2.mp3
├── 3.mp3
└── ...
and YOUR_DATASET/alignment.json
should look like:
{
"./datasets/YOUR_DATASET/audio/001.mp3": "My name is Taehoon Kim.",
"./datasets/YOUR_DATASET/audio/002.mp3": "The buses aren't the problem.",
"./datasets/YOUR_DATASET/audio/003.mp3": "They have discovered a new particle.",
}
After you prepare as described, you should genearte preprocessed data with:
python3 -m datasets.generate_data ./datasets/YOUR_DATASET/alignment.json
You can generate datasets for 3 public Korean figures including:
- Sohn Suk-hee: anchor and president of JTBC
- Park Geun-hye: a former President of South Korea
- Moon Jae-in: the current President of South Korea
Each dataset can be generated with following scripts:
./scripts/prepare_son.sh # Sohn Suk-hee
./scripts/prepare_park.sh # Park Geun-hye
./scripts/prepare_moon.sh # Moon Jae-in
Each script execute below commands. (explain with son
dataset)
-
To automate an alignment between sounds and texts, prepare
GOOGLE_APPLICATION_CREDENTIALS
to use Google Speech Recognition API. To get credentials, read this.export GOOGLE_APPLICATION_CREDENTIALS="YOUR-GOOGLE.CREDENTIALS.json"
-
Download speech(or video) and text.
python3 -m datasets.son.download
-
Segment all audios on silence.
python3 -m audio.silence --audio_pattern "./datasets/son/audio/*.wav" --method=pydub
-
By using Google Speech Recognition API, we predict sentences for all segmented audios. (this is optional for
moon
andpark
because they already haverecognition.json
)python3 -m recognition.google --audio_pattern "./datasets/son/audio/*.*.wav"
-
By comparing original text and recognised text, save
audio<->text
pair information into./datasets/son/alignment.json
.python3 -m recognition.alignment --recognition_path "./datasets/son/recognition.json" --score_threshold=0.5
-
Finally, generated numpy files which will be used in training.
python3 -m datasets.generate_data ./datasets/son/alignment.json
Because the automatic generation is extremely naive, the dataset is noisy. However, if you have enough datasets (20+ hours with random initialization or 5+ hours with pretrained model initialization), you can expect an acceptable quality of audio synthesis.
You can download a pre-trained models or generate audio. Available models are:
-
Single speaker model for Sohn Suk-hee.
python3 download.py son
-
Single speaker model for Park Geun-hye.
python3 download.py park
After you donwload pre-trained models, you can generate voices as follows:
python3 synthesizer.py --load_path logs/son-20171015 --text "이거 실화냐?"
python3 synthesizer.py --load_path logs/park-20171015 --text "이거 실화냐?"
WARNING: The two pre-trained models are being made available for research purpose only.
The important hyperparameters for a models are defined in hparams.py
.
To train a single-speaker model:
python3 train.py --data_path=datasets/jtbc
python3 train.py --data_path=datasets/park --initialize_path=PATH_TO_CHECKPOINT
To train a multi-speaker model:
# after change `model_type` in `hparams.py` to `deepvoice` or `simple`
python3 train.py --data_path=datasets/jtbc,datasets/park
To restart a training from previous experiments such as logs/son-20171015
:
python3 train.py --data_path=datasets/son --load_path logs/son-20171015
If you don't have good and enough (10+ hours) dataset, it would be better to use --initialize_path
to use a well-trained model as initial parameters.
You can train your own models with:
python3 app.py --load_path logs/park-20171015 --num_speakers=1
or generate audio directly with:
python3 synthesizer.py --load_path logs/park-20171015 --text "이거 실화냐?"
This is not an official DEVSISTERS product. This project is not responsible for misuse or for any damage that you may cause. You agree that you use this software at your own risk.
- Keith Ito's tacotron
- DEVIEW 2017 presentation (Korean)
Taehoon Kim / @carpedm20