b6c020901a
* various fixes to ContextGraph to support open vocabulary keywords decoder * Add keyword spotter runtime * Add binary * First version works * Minor fixes * update text2token * default values * Add jni for kws * add kws android project * Minor fixes * Remove unused interface * Minor fixes * Add workflow * handle extra info in texts * Minor fixes * Add more comments * Fix ci * fix cpp style * Add input box in android demo so that users can specify their keywords * Fix cpp style * Fix comments * Minor fixes * Minor fixes * minor fixes * Minor fixes * Minor fixes * Add CI * Fix code style * cpplint * Fix comments * Fix error
69 lines
2.1 KiB
Bash
Executable File
69 lines
2.1 KiB
Bash
Executable File
#!/usr/bin/env bash
|
||
|
||
set -e
|
||
|
||
log() {
|
||
# This function is from espnet
|
||
local fname=${BASH_SOURCE[1]##*/}
|
||
echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
|
||
}
|
||
|
||
echo "EXE is $EXE"
|
||
echo "PATH: $PATH"
|
||
|
||
which $EXE
|
||
|
||
log "------------------------------------------------------------"
|
||
log "Run Chinese keyword spotting (Wenetspeech）"
|
||
log "------------------------------------------------------------"
|
||
|
||
repo_url=https://www.modelscope.cn/pkufool/sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.git
|
||
log "Start testing ${repo_url}"
|
||
repo=sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01
|
||
log "Download pretrained model and test-data from $repo_url"
|
||
|
||
GIT_LFS_SKIP_SMUDGE=1 git clone $repo_url
|
||
pushd $repo
|
||
git lfs pull --include "*.onnx"
|
||
ls -lh *.onnx
|
||
popd
|
||
|
||
time $EXE \
|
||
--tokens=$repo/tokens.txt \
|
||
--encoder=$repo/encoder-epoch-12-avg-2-chunk-16-left-64.onnx \
|
||
--decoder=$repo/decoder-epoch-12-avg-2-chunk-16-left-64.onnx \
|
||
--joiner=$repo/joiner-epoch-12-avg-2-chunk-16-left-64.onnx \
|
||
--keywords-file=$repo/test_wavs/test_keywords.txt \
|
||
--max-active-paths=4 \
|
||
--num-threads=4 \
|
||
$repo/test_wavs/3.wav $repo/test_wavs/4.wav $repo/test_wavs/5.wav $repo/test_wavs/6.wav
|
||
|
||
rm -rf $repo
|
||
|
||
log "------------------------------------------------------------"
|
||
log "Run English keyword spotting (Gigaspeech）"
|
||
log "------------------------------------------------------------"
|
||
|
||
repo_url=https://www.modelscope.cn/pkufool/sherpa-onnx-kws-zipformer-gigaspeech-3.3M-2024-01-01.git
|
||
log "Start testing ${repo_url}"
|
||
repo=sherpa-onnx-kws-zipformer-gigaspeech-3.3M-2024-01-01
|
||
log "Download pretrained model and test-data from $repo_url"
|
||
|
||
GIT_LFS_SKIP_SMUDGE=1 git clone $repo_url
|
||
pushd $repo
|
||
git lfs pull --include "*.onnx"
|
||
ls -lh *.onnx
|
||
popd
|
||
|
||
time $EXE \
|
||
--tokens=$repo/tokens.txt \
|
||
--encoder=$repo/encoder-epoch-12-avg-2-chunk-16-left-64.onnx \
|
||
--decoder=$repo/decoder-epoch-12-avg-2-chunk-16-left-64.onnx \
|
||
--joiner=$repo/joiner-epoch-12-avg-2-chunk-16-left-64.onnx \
|
||
--keywords-file=$repo/test_wavs/test_keywords.txt \
|
||
--max-active-paths=4 \
|
||
--num-threads=4 \
|
||
$repo/test_wavs/0.wav $repo/test_wavs/1.wav
|
||
|
||
rm -rf $repo
|