--voc_stat VOC_STAT mean and standard deviation used to normalize
spectrogram when training voc.
...
...
@@ -208,9 +206,9 @@ optional arguments:
output dir.
```
1.`--am` is acoustic model type with the format {model_name}_{dataset}
2.`--am_config`, `--am_checkpoint`, `--am_stat`, `--phones_dict``--speaker_dict` are arguments for acoustic model, which correspond to the 5 files in the fastspeech2 pretrained model.
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_checkpoint`, `--voc_stat` are arguments for vocoder, which correspond to the 3 files in the parallel wavegan pretrained model.
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`.
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.
--voc_stat VOC_STAT mean and standard deviation used to normalize
spectrogram when training voc.
...
...
@@ -198,9 +196,9 @@ optional arguments:
output dir.
```
1.`--am` is acoustic model type with the format {model_name}_{dataset}
2.`--am_config`, `--am_checkpoint`, `--am_stat` and `--phones_dict` are arguments for acoustic model, which correspond to the 4 files in the Tacotron2 pretrained model.
2.`--am_config`, `--am_ckpt`, `--am_stat` and `--phones_dict` are arguments for acoustic model, which correspond to the 4 files in the Tacotron2 pretrained model.
3.`--voc` is vocoder type with the format {model_name}_{dataset}
4.`--voc_config`, `--voc_checkpoint`, `--voc_stat` are arguments for vocoder, which correspond to the 3 files in the parallel wavegan pretrained model.
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`.
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.
--voc_stat VOC_STAT mean and standard deviation used to normalize
spectrogram when training voc.
...
...
@@ -204,9 +202,9 @@ optional arguments:
output dir.
```
1.`--am` is acoustic model type with the format {model_name}_{dataset}
2.`--am_config`, `--am_checkpoint`, `--am_stat`, `--phones_dict` and `--tones_dict` are arguments for acoustic model, which correspond to the 5 files in the speedyspeech pretrained model.
2.`--am_config`, `--am_ckpt`, `--am_stat`, `--phones_dict` and `--tones_dict` are arguments for acoustic model, which correspond to the 5 files in the speedyspeech pretrained model.
3.`--voc` is vocoder type with the format {model_name}_{dataset}
4.`--voc_config`, `--voc_checkpoint`, `--voc_stat` are arguments for vocoder, which correspond to the 3 files in the parallel wavegan pretrained model.
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`.
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.
--voc_stat VOC_STAT mean and standard deviation used to normalize
spectrogram when training voc.
...
...
@@ -204,11 +202,12 @@ optional arguments:
--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_checkpoint`, `--am_stat` and `--phones_dict` are arguments for acoustic model, which correspond to the 4 files in the fastspeech2 pretrained model.
2.`--am_config`, `--am_ckpt`, `--am_stat` and `--phones_dict` are arguments for acoustic model, which correspond to the 4 files in the fastspeech2 pretrained model.
3.`--voc` is vocoder type with the format {model_name}_{dataset}
4.`--voc_config`, `--voc_checkpoint`, `--voc_stat` are arguments for vocoder, which correspond to the 3 files in the parallel wavegan pretrained model.
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`.
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.
This example contains code used to train a [VITS](https://arxiv.org/abs/2106.06103) model with [Chinese Standard Mandarin Speech Copus](https://www.data-baker.com/open_source.html).
## Dataset
### Download and Extract
Download CSMSC from it's [Official Website](https://test.data-baker.com/data/index/source).
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get phonemes for VITS, the durations of MFA are not needed here.
You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
## Get Started
Assume the path to the dataset is `~/datasets/BZNSYP`.
Assume the path to the MFA result of CSMSC is `./baker_alignment_tone`.
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 a 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
├── feats_stats.npy
├── norm
└── raw
```
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 wave and linear spectrogram 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/feats_stats.npy`.
Also, there is a `metadata.jsonl` in each subfolder. It is a table-like file that contains phones, text_lengths, feats, feats_lengths, the path of linear spectrogram features, the path of raw waves, speaker, and the id of each utterance.
--voc_stat VOC_STAT mean and standard deviation used to normalize
spectrogram when training voc.
...
...
@@ -198,9 +196,9 @@ optional arguments:
output dir.
```
1.`--am` is acoustic model type with the format {model_name}_{dataset}
2.`--am_config`, `--am_checkpoint`, `--am_stat` and `--phones_dict` are arguments for acoustic model, which correspond to the 4 files in the Tacotron2 pretrained model.
2.`--am_config`, `--am_ckpt`, `--am_stat` and `--phones_dict` are arguments for acoustic model, which correspond to the 4 files in the Tacotron2 pretrained model.
3.`--voc` is vocoder type with the format {model_name}_{dataset}
4.`--voc_config`, `--voc_checkpoint`, `--voc_stat` are arguments for vocoder, which correspond to the 3 files in the parallel wavegan pretrained model.
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`.
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.
--voc_stat VOC_STAT mean and standard deviation used to normalize
spectrogram when training voc.
...
...
@@ -204,9 +202,9 @@ optional arguments:
output dir.
```
1. `--am` is acoustic model type with the format {model_name}_{dataset}
2. `--am_config`, `--am_checkpoint`, `--am_stat` and `--phones_dict` are arguments for acoustic model, which correspond to the 4 files in the fastspeech2 pretrained model.
2. `--am_config`, `--am_ckpt`, `--am_stat` and `--phones_dict` are arguments for acoustic model, which correspond to the 4 files in the fastspeech2 pretrained model.
3. `--voc` is vocoder type with the format {model_name}_{dataset}
4. `--voc_config`, `--voc_checkpoint`, `--voc_stat` are arguments for vocoder, which correspond to the 3 files in the parallel wavegan pretrained model.
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`.
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.
--voc_stat VOC_STAT mean and standard deviation used to normalize
spectrogram when training voc.
...
...
@@ -207,9 +205,9 @@ optional arguments:
output dir.
```
1.`--am` is acoustic model type with the format {model_name}_{dataset}
2.`--am_config`, `--am_checkpoint`, `--am_stat`, `--phones_dict``--speaker_dict` are arguments for acoustic model, which correspond to the 5 files in the fastspeech2 pretrained model.
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_checkpoint`, `--voc_stat` are arguments for vocoder, which correspond to the 3 files in the parallel wavegan pretrained model.
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`.
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.
@@ -44,13 +44,13 @@ More details please see `README.md` under `examples`.
> If using docker please check `--privileged` is set when `docker run`.
* Fatal error at startup: `a function redirection which is mandatory for this platform-tool combination cannot be set up`
```
```bash
apt-get install libc6-dbg
```
* Install
```
```bash
pushd tools
./setup_valgrind.sh
popd
...
...
@@ -59,4 +59,4 @@ popd
## TODO
### Deepspeech2 with linear feature
* DecibelNormalizer: there is a little bit difference between offline and online db norm. The computation of online db norm read feature chunk by chunk, which causes the feature size is different with offline db norm. In normalizer.cc:73, the samples.size() is different, which causes the difference of result.
* DecibelNormalizer: there is a small difference between the offline and online db norm. The computation of online db norm reads features chunk by chunk, which causes the feature size to be different different with offline db norm. In `normalizer.cc:73`, the `samples.size()` is different, which causes the different result.
