parent
b105c63eb6
commit
d028c8416d
@ -1,20 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
|
|
||||||
source path.sh
|
|
||||||
|
|
||||||
# run on MacOS
|
|
||||||
# brew install portaudio
|
|
||||||
# pip install pyaudio
|
|
||||||
# pip install keyboard
|
|
||||||
|
|
||||||
# start demo client
|
|
||||||
python3 -u ${BIN_DIR}/deploy/client.py \
|
|
||||||
--host_ip="localhost" \
|
|
||||||
--host_port=8086 \
|
|
||||||
|
|
||||||
if [ $? -ne 0 ]; then
|
|
||||||
echo "Failed in starting demo client!"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
exit 0
|
|
@ -1,40 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
# TODO: replace the model with a mandarin model
|
|
||||||
|
|
||||||
if [[ $# != 1 ]];then
|
|
||||||
echo "usage: $1 checkpoint_path"
|
|
||||||
exit -1
|
|
||||||
fi
|
|
||||||
|
|
||||||
source path.sh
|
|
||||||
|
|
||||||
# download language model
|
|
||||||
bash local/download_lm_ch.sh
|
|
||||||
if [ $? -ne 0 ]; then
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
# download well-trained model
|
|
||||||
#bash local/download_model.sh
|
|
||||||
#if [ $? -ne 0 ]; then
|
|
||||||
# exit 1
|
|
||||||
#fi
|
|
||||||
|
|
||||||
# start demo server
|
|
||||||
CUDA_VISIBLE_DEVICES=0 \
|
|
||||||
python3 -u ${BIN_DIR}/deploy/server.py \
|
|
||||||
--device 'gpu' \
|
|
||||||
--nproc 1 \
|
|
||||||
--config conf/deepspeech2.yaml \
|
|
||||||
--host_ip="localhost" \
|
|
||||||
--host_port=8086 \
|
|
||||||
--speech_save_dir="demo_cache" \
|
|
||||||
--checkpoint_path ${1}
|
|
||||||
|
|
||||||
if [ $? -ne 0 ]; then
|
|
||||||
echo "Failed in starting demo server!"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
|
|
||||||
exit 0
|
|
@ -1,28 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
|
|
||||||
# grid-search for hyper-parameters in language model
|
|
||||||
python3 -u ${BIN_DIR}/tune.py \
|
|
||||||
--device 'gpu' \
|
|
||||||
--nproc 1 \
|
|
||||||
--config conf/deepspeech2.yaml \
|
|
||||||
--num_batches=10 \
|
|
||||||
--batch_size=128 \
|
|
||||||
--beam_size=300 \
|
|
||||||
--num_proc_bsearch=8 \
|
|
||||||
--num_alphas=10 \
|
|
||||||
--num_betas=10 \
|
|
||||||
--alpha_from=0.0 \
|
|
||||||
--alpha_to=5.0 \
|
|
||||||
--beta_from=-6 \
|
|
||||||
--beta_to=6 \
|
|
||||||
--cutoff_prob=1.0 \
|
|
||||||
--cutoff_top_n=40 \
|
|
||||||
--checkpoint_path ${1}
|
|
||||||
|
|
||||||
if [ $? -ne 0 ]; then
|
|
||||||
echo "Failed in tuning!"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
|
|
||||||
exit 0
|
|
@ -1,10 +1,17 @@
|
|||||||
# LibriSpeech
|
# LibriSpeech
|
||||||
|
|
||||||
|
## Data
|
||||||
|
| Data Subset | Duration in Seconds |
|
||||||
|
| --- | --- |
|
||||||
|
| data/manifest.train | 0.83s ~ 29.735s |
|
||||||
|
| data/manifest.dev | 1.065 ~ 35.155s |
|
||||||
|
| data/manifest.test-clean | 1.285s ~ 34.955s |
|
||||||
|
|
||||||
## Deepspeech2
|
## Deepspeech2
|
||||||
|
|
||||||
| Model | Params | release | Config | Test set | Loss | WER |
|
| Model | Params | release | Config | Test set | Loss | WER |
|
||||||
| --- | --- | --- | --- | --- | --- | --- |
|
| --- | --- | --- | --- | --- | --- | --- |
|
||||||
| DeepSpeech2 | 42.96M | 2.2.0 | conf/deepspeech2.yaml + spec_aug | 14.49190807 | test-clean | 0.067283 |
|
| DeepSpeech2 | 42.96M | 2.2.0 | conf/deepspeech2.yaml + spec_aug | test-clean | 14.49190807 | 0.067283 |
|
||||||
| DeepSpeech2 | 42.96M | 2.1.0 | conf/deepspeech2.yaml | 15.184467315673828 | test-clean | 0.072154 |
|
| DeepSpeech2 | 42.96M | 2.1.0 | conf/deepspeech2.yaml | test-clean | 15.184467315673828 | 0.072154 |
|
||||||
| DeepSpeech2 | 42.96M | 2.0.0 | conf/deepspeech2.yaml | - | test-clean | 0.073973 |
|
| DeepSpeech2 | 42.96M | 2.0.0 | conf/deepspeech2.yaml | test-clean | - | 0.073973 |
|
||||||
| DeepSpeech2 | 42.96M | 1.8.5 | - | test-clean | - | 0.074939 |
|
| DeepSpeech2 | 42.96M | 1.8.5 | - | test-clean | - | 0.074939 |
|
||||||
|
@ -1,33 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
|
|
||||||
if [ $# != 1 ];then
|
|
||||||
echo "usage: tune ckpt_path"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
# grid-search for hyper-parameters in language model
|
|
||||||
python3 -u ${BIN_DIR}/tune.py \
|
|
||||||
--device 'gpu' \
|
|
||||||
--nproc 1 \
|
|
||||||
--config conf/deepspeech2.yaml \
|
|
||||||
--num_batches=-1 \
|
|
||||||
--batch_size=128 \
|
|
||||||
--beam_size=500 \
|
|
||||||
--num_proc_bsearch=12 \
|
|
||||||
--num_alphas=45 \
|
|
||||||
--num_betas=8 \
|
|
||||||
--alpha_from=1.0 \
|
|
||||||
--alpha_to=3.2 \
|
|
||||||
--beta_from=0.1 \
|
|
||||||
--beta_to=0.45 \
|
|
||||||
--cutoff_prob=1.0 \
|
|
||||||
--cutoff_top_n=40 \
|
|
||||||
--checkpoint_path ${1}
|
|
||||||
|
|
||||||
if [ $? -ne 0 ]; then
|
|
||||||
echo "Failed in tuning!"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
|
|
||||||
exit 0
|
|
@ -1,3 +1,3 @@
|
|||||||
# Punctation Restoration
|
# Punctation Restoration
|
||||||
|
|
||||||
Please using `https://github.com/745165806/PaddleSpeechTask` to do this task.
|
Please using [PaddleSpeechTask](https://github.com/745165806/PaddleSpeechTask] to do this task.
|
||||||
|
Loading…
Reference in new issue