-
Notifications
You must be signed in to change notification settings - Fork 2.9k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #55 from xinghai-sun/ds2
Add audio data provider and a simplified DeepSpeech2 model configuration.
- Loading branch information
Showing
8 changed files
with
1,079 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,58 @@ | ||
# Deep Speech 2 on PaddlePaddle | ||
|
||
## Quick Start | ||
|
||
### Installation | ||
|
||
Please replace `$PADDLE_INSTALL_DIR` with your paddle installation directory. | ||
|
||
``` | ||
pip install -r requirements.txt | ||
export LD_LIBRARY_PATH=$PADDLE_INSTALL_DIR/Paddle/third_party/install/warpctc/lib:$LD_LIBRARY_PATH | ||
``` | ||
|
||
For some machines, we also need to install libsndfile1. Details to be added. | ||
|
||
### Preparing Dataset(s) | ||
|
||
``` | ||
python librispeech.py | ||
``` | ||
|
||
More help for arguments: | ||
|
||
``` | ||
python librispeech.py --help | ||
``` | ||
|
||
### Traininig | ||
|
||
For GPU Training: | ||
|
||
``` | ||
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --trainer_count 4 | ||
``` | ||
|
||
For CPU Training: | ||
|
||
``` | ||
python train.py --trainer_count 8 --use_gpu False | ||
``` | ||
|
||
More help for arguments: | ||
|
||
``` | ||
python train.py --help | ||
``` | ||
|
||
### Inferencing | ||
|
||
``` | ||
python infer.py | ||
``` | ||
|
||
More help for arguments: | ||
|
||
``` | ||
python infer.py --help | ||
``` |
Oops, something went wrong.