[ERNIE-SAT](https://arxiv.org/abs/2211.03545) speech-text joint pretraining framework, which achieves SOTA results in cross-lingual multi-speaker speech synthesis and cross-lingual speech editing tasks, It can be applied to a series of scenarios such as Speech Editing, personalized Speech Synthesis, and Voice Cloning.
- In the pretraining process, the phonemes corresponding to Chinese and English are used as input to achieve cross-language and personalized soft phoneme mapping
- The joint mask learning of speech and text is used to realize the alignment of speech and text
Download VCTK-0.92 from it's [Official Website](https://datashare.ed.ac.uk/handle/10283/3443) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/VCTK-Corpus-0.92`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for fastspeech2.
You can download from here [vctk_alignment.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/VCTK-Corpus-0.92/vctk_alignment.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
ps: we remove three speakers in VCTK-0.92 (see [reorganize_vctk.py](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/examples/other/mfa/local/reorganize_vctk.py)):
1.`p315`, because of no text for it.
2.`p280` and `p362`, because no *_mic2.flac (which is better than *_mic1.flac) for them.
## Get Started
Assume the path to the dataset is `~/datasets/VCTK-Corpus-0.92`.
Assume the path to the MFA result of VCTK is `./vctk_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 ${conf_path}
```
When it is done. A `dump` folder is created in the current directory. The structure of the dump folder is listed below.
```text
dump
├── dev
│ ├── norm
│ └── raw
├── phone_id_map.txt
├── speaker_id_map.txt
├── test
│ ├── norm
│ └── raw
└── train
├── norm
├── raw
└── speech_stats.npy
```
The dataset is split into 3 parts, namely `train`, `dev`, and` test`, each of which contains a `norm` and `raw` subfolder. The raw folder contains speech features of each utterance, while the norm folder contains normalized ones. The statistics used to normalize features are computed from the training set, which is located in `dump/train/*_stats.npy`.
Also, there is a `metadata.jsonl` in each subfolder. It is a table-like file that contains phones, text_lengths, speech_lengths, durations, the path of speech features, speaker, and id of each utterance.
We use [HiFiGAN](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/vctk/voc5) as the neural vocoder.
Download pretrained HiFiGAN model from [hifigan_vctk_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_vctk_ckpt_0.2.0.zip) and unzip it.
```bash
unzip hifigan_vctk_ckpt_0.2.0.zip
```
HiFiGAN checkpoint contains files listed below.
```text
hifigan_vctk_ckpt_0.2.0
├── default.yaml # default config used to train HiFiGAN
├── feats_stats.npy # statistics used to normalize spectrogram when training HiFiGAN
└── snapshot_iter_2500000.pdz # generator parameters of HiFiGAN
```
`./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`.
You can check the text of downloaded wavs in `source/README.md`.
### Speech Synthesis and Speech Editing
```bash
./run.sh --stage 3 --stop-stage 3 --gpus 0
```
`stage 3` of `run.sh` calls `local/synthesize_e2e.sh`, `stage 0` of it is **Speech Synthesis** and `stage 1` of it is **Speech Editing**.
You can modify `--wav_path`、`--old_str` and `--new_str` yourself, `--old_str` should be the text corresponding to the audio of `--wav_path`, `--new_str` should be designed according to `--task_name`, both `--source_lang` and `--target_lang` should be `en` for model trained with VCTK dataset.
