msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity

fix

Browse Source
pull/3930/head
enkilee 10 months ago
parent fb36911f35
commit 7cb947505c
2 changed files with 23 additions and 23 deletions
Show Stats Download Patch File Download Diff File

42
examples/timit/asr1/README.md
Unescape View File

@ -3,7 +3,7 @@ The phoneme-based continuous speech corpus is a collaboration between Texas Inst
## Dataset ## Dataset
### Download and Extract ### Download and Extract
Download TIMIT from it's [official website](https://catalog.ldc.upenn.edu/LDC93S1) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/timit`. Download TIMIT from it's [official website](https://catalog.ldc.upenn.edu/LDC93S1) and extract it to `~/datasets`. Assume unzip the dataset in the directory `~/datasets/timit`.
## Overview ## Overview
All the scripts you need are in `run.sh`. There are several stages in `run.sh`, and each stage has its function. All the scripts you need are in `run.sh`. There are several stages in `run.sh`, and each stage has its function.
@ -50,7 +50,7 @@ You can set the local variables (except `ckpt`) when you use `run.sh`
For example, you can set the `gpus` and `avg_num` when you use the command line.: For example, you can set the `gpus` and `avg_num` when you use the command line.:
```bash ```bash
bash run.sh --gpus 0,1 --avg_num 20 bash run.sh --gpus 0,1,2,3 --avg_num 10
``` ```
## Stage 0: Data Processing ## Stage 0: Data Processing
To use this example, you need to process data firstly and you can use stage 0 in `run.sh` to do this. The code is shown below: To use this example, you need to process data firstly and you can use stage 0 in `run.sh` to do this. The code is shown below:
@ -71,7 +71,7 @@ bash run.sh --stage 0 --stop_stage 0
You can also just run these scripts in your command line. You can also just run these scripts in your command line.
```bash ```bash
source path.sh source path.sh
bash ./local/timit_data_prep.sh /path/to/TIMIT bash ./local/timit_data_prep.sh ${TIMIT_path}
bash ./local/data.sh bash ./local/data.sh
``` ```
After processing the data, the ``data`` directory will look like this: After processing the data, the ``data`` directory will look like this:
@ -116,12 +116,12 @@ If you want to train the model, you can use the script below to execute stage 0
```bash ```bash
bash run.sh --stage 0 --stop_stage 1 bash run.sh --stage 0 --stop_stage 1
``` ```
or you can run these scripts in the command line (only use CPU). or you can run these scripts in the command line.
```bash ```bash
source path.sh source path.sh
bash ./local/timit_data_prep.sh /path/to/TIMIT bash ./local/timit_data_prep.sh ${TIMIT_path}
bash ./local/data.sh bash ./local/data.sh
CUDA_VISIBLE_DEVICES= ./local/train.sh conf/transformer.yaml transformer CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh conf/transformer.yaml transformer
``` ```
## Stage 2: Top-k Models Averaging ## Stage 2: Top-k Models Averaging
After training the model, we need to get the final model for testing and inference. In every epoch, the model checkpoint is saved, so we can choose the best model from them based on the validation loss or we can sort them and average the parameters of the top-k models to get the final model. We can use stage 2 to do this, and the code is shown below: After training the model, we need to get the final model for testing and inference. In every epoch, the model checkpoint is saved, so we can choose the best model from them based on the validation loss or we can sort them and average the parameters of the top-k models to get the final model. We can use stage 2 to do this, and the code is shown below:
@ -136,13 +136,13 @@ If you want to get the final model, you can use the script below to execute stag
```bash ```bash
bash run.sh --stage 0 --stop_stage 2 bash run.sh --stage 0 --stop_stage 2
``` ```
or you can run these scripts in the command line (only use CPU). or you can run these scripts in the command line.
```bash ```bash
bash ./local/timit_data_prep.sh /path/to/TIMIT bash ./local/timit_data_prep.sh ${TIMIT_path}
source path.sh source path.sh
bash ./local/data.sh bash ./local/data.sh
CUDA_VISIBLE_DEVICES= ./local/train.sh conf/transformer.yaml transformer CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh conf/transformer.yaml transformer
avg.sh best exp/conformer/checkpoints 20 avg.sh best exp/conformer/checkpoints 10
``` ```
## Stage 3: Model Testing ## Stage 3: Model Testing
The test stage is to evaluate the model performance. The code of the test stage is shown below: The test stage is to evaluate the model performance. The code of the test stage is shown below:
@ -156,14 +156,14 @@ If you want to train a model and test it, you can use the script below to execut
```bash ```bash
bash run.sh --stage 0 --stop_stage 3 bash run.sh --stage 0 --stop_stage 3
``` ```
or you can run these scripts in the command line (only use CPU). or you can run these scripts in the command line.
```bash ```bash
source path.sh source path.sh
bash ./local/timit_data_prep.sh /path/to/TIMIT bash ./local/timit_data_prep.sh ${TIMIT_path}
bash ./local/data.sh bash ./local/data.sh
CUDA_VISIBLE_DEVICES= ./local/train.sh conf/transformer.yaml transformer CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh conf/transformer.yaml transformer
avg.sh best exp/transformer/checkpoints 20 avg.sh best exp/transformer/checkpoints 10
CUDA_VISIBLE_DEVICES= ./local/test.sh conf/transformer.yaml exp/transformer/checkpoints/avg_20 CUDA_VISIBLE_DEVICES=0 ./local/test.sh conf/transformer.yaml exp/transformer/checkpoints/avg_10
``` ```
## Stage 4: CTC Alignment ## Stage 4: CTC Alignment
If you want to get the alignment between the audio and the text, you can use the ctc alignment. The code of this stage is shown below: If you want to get the alignment between the audio and the text, you can use the ctc alignment. The code of this stage is shown below:
@ -182,14 +182,14 @@ or if you only need to train a model and do the alignment, you can use these scr
bash run.sh --stage 0 --stop_stage 2 bash run.sh --stage 0 --stop_stage 2
bash run.sh --stage 4 --stop_stage 4 bash run.sh --stage 4 --stop_stage 4
``` ```
or you can also use these scripts in the command line (only use CPU). or you can also use these scripts in the command line.
```bash ```bash
source path.sh source path.sh
bash ./local/timit_data_prep.sh /path/to/TIMIT bash ./local/timit_data_prep.sh ${TIMIT_path}
bash ./local/data.sh bash ./local/data.sh
CUDA_VISIBLE_DEVICES= ./local/train.sh conf/transformer.yaml transformer CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh conf/transformer.yaml transformer
avg.sh best exp/transformer/checkpoints 20 avg.sh best exp/transformer/checkpoints 10
# test stage is optional # test stage is optional
CUDA_VISIBLE_DEVICES= ./local/test.sh conf/transformer.yaml exp/transformer/checkpoints/avg_20 CUDA_VISIBLE_DEVICES=0 ./local/test.sh conf/transformer.yaml exp/transformer/checkpoints/avg_10
CUDA_VISIBLE_DEVICES= ./local/align.sh conf/transformer.yaml exp/transformer/checkpoints/avg_20 CUDA_VISIBLE_DEVICES=0 ./local/align.sh conf/transformer.yaml exp/transformer/checkpoints/avg_10
``` ```

2
examples/timit/asr1/run.sh
Unescape View File

@ -9,7 +9,7 @@ stop_stage=50
conf_path=conf/transformer.yaml conf_path=conf/transformer.yaml
decode_conf_path=conf/tuning/decode.yaml decode_conf_path=conf/tuning/decode.yaml
avg_num=10 avg_num=10
TIMIT_path=/path/to/TIMIT TIMIT_path=~/datasets/timit/data/lisa/data/timit/raw/TIMIT
. ${MAIN_ROOT}/utils/parse_options.sh || exit 1; . ${MAIN_ROOT}/utils/parse_options.sh || exit 1;

Write Preview
Loading…
Cancel
Save