Merge pull request #1077 from yt605155624/fix_docs

[demos]rm big sources in demos
pull/1078/head
TianYuan 3 years ago committed by GitHub
commit 45b8cd2646
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

Binary file not shown.

Before

Width:  |  Height:  |  Size: 441 KiB

@ -0,0 +1,7 @@
# Metaverse
You can make your favorite person say the specified content with the `TTS` mudule of `PaddleSpeech` and `PaddleGAN`, and construct your own virtual human.
Run the following command line to get started:
```
./run.sh
```

@ -29,6 +29,9 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
unzip -d download download/pwg_baker_ckpt_0.4.zip
wget -P download https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_nosil_baker_ckpt_0.4.zip
unzip -d download download/fastspeech2_nosil_baker_ckpt_0.4.zip
# donload sources
wget -P dowload https://paddlespeech.bj.bcebos.com/demos/metaverse/Lamarr.png
fi
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
@ -54,7 +57,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
CUDA_VISIBLE_DEVICES=${gpus} \
python3 PaddleGAN/applications/tools/wav2lip.py \
--checkpoint_path download/wav2lip_hq.pdparams \
--face Lamarr.png \
--face dowload/Lamarr.png \
--audio output/wavs/000.wav \
--outfile output/tts_lips.mp4 \
--face_enhancement

@ -0,0 +1,7 @@
# Story Talker
You can use `PaddleOCR` to get the text of a storybook, and read it by the `TTS` mudule of `PaddleSpeech`.
Run the following command line to get started:
```
./run.sh
```

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.5 MiB

@ -23,12 +23,15 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
unzip -d download download/pwg_baker_ckpt_0.4.zip
wget -P download https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_nosil_baker_ckpt_0.4.zip
unzip -d download download/fastspeech2_nosil_baker_ckpt_0.4.zip
# download sources
wget -P download https://paddlespeech.bj.bcebos.com/demos/story_talker/simfang.ttf
wget -P download/imgs https://paddlespeech.bj.bcebos.com/demos/story_talker/000.jpg
fi
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
# run ocr
CUDA_VISIBLE_DEVICES=${gpus} \
python3 ocr.py --img-dir=imgs --output-dir=output --font-path=simfang.ttf
python3 ocr.py --img-dir=download/imgs --output-dir=output --font-path=download/simfang.ttf
fi
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then

Binary file not shown.

@ -132,4 +132,3 @@ popd
- Make sure these libraries or tools in [dependencies](./dependencies.md) installed. More information please see: `setup.py `and `tools/Makefile`.
- The version of `swig` should >= 3.0
- we will simplify the install process in the future.

Binary file not shown.

Before

Width:  |  Height:  |  Size: 221 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 550 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 514 KiB

File diff suppressed because it is too large Load Diff
Loading…
Cancel
Save