This example contains code used to train a [Fastspeech2](https://arxiv.org/abs/2006.04558) model with [CSMSC](https://www.data-baker.com/open_source.html), [LJSpeech-1.1](https://keithito.com/LJ-Speech-Dataset/), [AISHELL3](http://www.aishelltech.com/aishell_3) and [VCTK](https://datashare.ed.ac.uk/handle/10283/3443) datasets.
Download all datasets and extract it to `~/datasets`. The CSMSC dataset is in the directory `~/datasets/BZNSYP`. The Ljspeech dataset is in the directory `~/datasets/LJSpeech-1.1`. The aishell3 dataset is in the directory `~/datasets/data_aishell3`. The vctk 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 the fastspeech2 training.
You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), [ljspeech_alignment.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/LJSpeech-1.1/ljspeech_alignment.tar.gz), [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz) and [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) (use MFA1.x now) of our repo.
## Get Started
Assume the paths of the datasets are `~/datasets/BZNSYP`, `~/datasets/LJSpeech-1.1`, `~/datasets/data_aishell3` and `~/datasets/VCTK-Corpus-0.92`.
Assume the path to the MFA result of the datasets are `./mfa_results/baker_alignment_tone`, `./mfa_results/ljspeech_alignment`, `./mfa_results/aishell3_alignment_tone` and `./mfa_results/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.
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.
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.
5.`--phones-dict` is the path of the phone vocabulary file.
6.`--speaker-dict` is the path of the speaker id map file when training a multi-speaker FastSpeech2.
### Synthesizing
We use [parallel wavegan](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc1) as the neural vocoder.
Download the pretrained parallel wavegan model from [pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip) and unzip it.
--voc_stat VOC_STAT mean and standard deviation used to normalize
spectrogram when training voc.
--lang LANG Choose model language. zh or en or mix
--inference_dir INFERENCE_DIR
dir to save inference models
--ngpu NGPU if ngpu == 0, use cpu.
--text TEXT text to synthesize, a 'utt_id sentence' pair per line.
--output_dir OUTPUT_DIR
output dir.
```
1.`--am` is acoustic model type with the format {model_name}_{dataset}
2.`--am_config`, `--am_ckpt`, `--am_stat`, `--phones_dict``--speaker_dict` are arguments for acoustic model, which correspond to the 5 files in the fastspeech2 pretrained model.
3.`--voc` is vocoder type with the format {model_name}_{dataset}
4.`--voc_config`, `--voc_ckpt`, `--voc_stat` are arguments for vocoder, which correspond to the 3 files in the parallel wavegan pretrained model.
5.`--lang` is the model language, which can be `zh` or `en` or `mix`.
6.`--test_metadata` should be the metadata file in the normalized subfolder of `test` in the `dump` folder.
7.`--text` is the text file, which contains sentences to synthesize.
8.`--output_dir` is the directory to save synthesized audio files.
9.`--ngpu` is the number of gpus to use, if ngpu == 0, use cpu.
## Pretrained Model
Pretrained FastSpeech2 model with no silence in the edge of audios: