fix readme

This commit is contained in:
TianYuan 2021-08-18 03:45:58 +00:00
parent 70b6ce64e4
commit 2482b112c0
1 changed files with 1 additions and 0 deletions

View File

@ -22,6 +22,7 @@ Run the command below to preprocess the dataset.
```bash ```bash
./run.sh ./run.sh
``` ```
If you want to train fastspeech2 with cpu, please add `--device=cpu` arguments for `python3 train.py` in `run.sh`.
## Synthesize ## Synthesize
We use [parallel wavegan](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/parallelwave_gan/baker) as the neural vocoder. We use [parallel wavegan](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/parallelwave_gan/baker) as the neural vocoder.
Download pretrained parallel wavegan model from [parallel_wavegan_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/parallel_wavegan_baker_ckpt_0.4.zip) and unzip it. Download pretrained parallel wavegan model from [parallel_wavegan_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/parallel_wavegan_baker_ckpt_0.4.zip) and unzip it.