mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
Export multi_zh-hans models to onnx
This commit is contained in:
Fangjun Kuang
parent
abd9437e6d
commit
9d4b0dfcd4
200
.github/scripts/multi-zh-hans.sh
vendored
200
.github/scripts/multi-zh-hans.sh
vendored
@ -1,200 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
set -ex
|
||||
|
||||
git config --global user.name "k2-fsa"
|
||||
git config --global user.email "csukuangfj@gmail.com"
|
||||
git config --global lfs.allowincompletepush true
|
||||
|
||||
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]}) $*"
|
||||
}
|
||||
|
||||
log "pwd: $PWD"
|
||||
|
||||
cd egs/multi_zh-hans/ASR
|
||||
|
||||
repo_url=https://huggingface.co/zrjin/icefall-asr-multi-zh-hans-zipformer-2023-9-2
|
||||
log "Downloading pre-trained model from $repo_url"
|
||||
GIT_LFS_SKIP_SMUDGE=1 git clone $repo_url
|
||||
repo=$(basename $repo_url)
|
||||
pushd $repo
|
||||
cd exp
|
||||
git lfs pull --include pretrained.pt
|
||||
ln -s pretrained.pt epoch-99.pt
|
||||
cd ../data/lang_bpe_2000
|
||||
ls -lh
|
||||
git lfs pull --include L.pt L_disambig.pt Linv.pt bpe.model
|
||||
git lfs pull --include "*.model"
|
||||
ls -lh
|
||||
popd
|
||||
|
||||
log "--------------------------------------------"
|
||||
log "Export non-streaming ONNX transducer models "
|
||||
log "--------------------------------------------"
|
||||
./zipformer/export-onnx.py \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
--use-averaged-model 0 \
|
||||
--epoch 99 \
|
||||
--avg 1 \
|
||||
--exp-dir $repo/exp \
|
||||
--causal False
|
||||
|
||||
ls -lh $repo/exp
|
||||
|
||||
./zipformer/onnx_pretrained.py \
|
||||
--encoder-model-filename $repo/exp/encoder-epoch-99-avg-1.onnx \
|
||||
--decoder-model-filename $repo/exp/decoder-epoch-99-avg-1.onnx \
|
||||
--joiner-model-filename $repo/exp/joiner-epoch-99-avg-1.onnx \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
$repo/test_wavs/DEV_T0000000000.wav \
|
||||
$repo/test_wavs/DEV_T0000000001.wav \
|
||||
$repo/test_wavs/DEV_T0000000002.wav \
|
||||
$repo/test_wavs/TEST_MEETING_T0000000113.wav \
|
||||
$repo/test_wavs/TEST_MEETING_T0000000219.wav \
|
||||
$repo/test_wavs/TEST_MEETING_T0000000351.wav
|
||||
|
||||
rm -rf $repo
|
||||
|
||||
repo_url=https://huggingface.co/zrjin/icefall-asr-multi-zh-hans-zipformer-ctc-streaming-2023-11-05
|
||||
log "Downloading pre-trained model from $repo_url"
|
||||
GIT_LFS_SKIP_SMUDGE=1 git clone $repo_url
|
||||
repo=$(basename $repo_url)
|
||||
|
||||
pushd $repo
|
||||
cd exp/
|
||||
git lfs pull --include pretrained.pt
|
||||
rm -fv epoch-20.pt
|
||||
rm -fv *.onnx
|
||||
ln -s pretrained.pt epoch-20.pt
|
||||
cd ../data/lang_bpe_2000
|
||||
ls -lh
|
||||
git lfs pull --include L.pt L_disambig.pt Linv.pt bpe.model
|
||||
git lfs pull --include "*.model"
|
||||
ls -lh
|
||||
popd
|
||||
|
||||
log "----------------------------------------"
|
||||
log "Export streaming ONNX CTC models "
|
||||
log "----------------------------------------"
|
||||
./zipformer/export-onnx-streaming-ctc.py \
|
||||
--exp-dir $repo/exp \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
--causal 1 \
|
||||
--avg 1 \
|
||||
--epoch 20 \
|
||||
--use-averaged-model 0 \
|
||||
--chunk-size 16 \
|
||||
--left-context-frames 128 \
|
||||
--use-ctc 1
|
||||
|
||||
ls -lh $repo/exp/
|
||||
|
||||
log "------------------------------------------------------------"
|
||||
log "Test exported streaming ONNX CTC models (greedy search) "
|
||||
log "------------------------------------------------------------"
|
||||
|
||||
test_wavs=(
|
||||
DEV_T0000000000.wav
|
||||
DEV_T0000000001.wav
|
||||
DEV_T0000000002.wav
|
||||
TEST_MEETING_T0000000113.wav
|
||||
TEST_MEETING_T0000000219.wav
|
||||
TEST_MEETING_T0000000351.wav
|
||||
)
|
||||
|
||||
for w in ${test_wavs[@]}; do
|
||||
./zipformer/onnx_pretrained-streaming-ctc.py \
|
||||
--model-filename $repo/exp/ctc-epoch-20-avg-1-chunk-16-left-128.int8.onnx \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
$repo/test_wavs/$w
|
||||
done
|
||||
|
||||
log "Upload onnx CTC models to huggingface"
|
||||
url=https://huggingface.co/k2-fsa/sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13
|
||||
GIT_LFS_SKIP_SMUDGE=1 git clone $url
|
||||
dst=$(basename $url)
|
||||
cp -v $repo/exp/ctc*.onnx $dst
|
||||
cp -v $repo/data/lang_bpe_2000/tokens.txt $dst
|
||||
cp -v $repo/data/lang_bpe_2000/bpe.model $dst
|
||||
mkdir -p $dst/test_wavs
|
||||
cp -v $repo/test_wavs/*.wav $dst/test_wavs
|
||||
cd $dst
|
||||
git lfs track "*.onnx" "bpe.model"
|
||||
ls -lh
|
||||
file bpe.model
|
||||
git status
|
||||
git add .
|
||||
git commit -m "upload model" && git push https://k2-fsa:${HF_TOKEN}@huggingface.co/k2-fsa/$dst main || true
|
||||
|
||||
log "Upload models to https://github.com/k2-fsa/sherpa-onnx"
|
||||
rm -rf .git
|
||||
rm -fv .gitattributes
|
||||
cd ..
|
||||
tar cjfv $dst.tar.bz2 $dst
|
||||
ls -lh *.tar.bz2
|
||||
mv -v $dst.tar.bz2 ../../../
|
||||
|
||||
log "----------------------------------------"
|
||||
log "Export streaming ONNX transducer models "
|
||||
log "----------------------------------------"
|
||||
|
||||
./zipformer/export-onnx-streaming.py \
|
||||
--exp-dir $repo/exp \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
--causal 1 \
|
||||
--avg 1 \
|
||||
--epoch 20 \
|
||||
--use-averaged-model 0 \
|
||||
--chunk-size 16 \
|
||||
--left-context-frames 128 \
|
||||
--use-ctc 0
|
||||
|
||||
ls -lh $repo/exp
|
||||
|
||||
log "------------------------------------------------------------"
|
||||
log "Test exported streaming ONNX transducer models (Python code)"
|
||||
log "------------------------------------------------------------"
|
||||
|
||||
log "test fp32"
|
||||
./zipformer/onnx_pretrained-streaming.py \
|
||||
--encoder-model-filename $repo/exp/encoder-epoch-20-avg-1-chunk-16-left-128.onnx \
|
||||
--decoder-model-filename $repo/exp/decoder-epoch-20-avg-1-chunk-16-left-128.onnx \
|
||||
--joiner-model-filename $repo/exp/joiner-epoch-20-avg-1-chunk-16-left-128.onnx \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
$repo/test_wavs/DEV_T0000000000.wav
|
||||
|
||||
log "test int8"
|
||||
./zipformer/onnx_pretrained-streaming.py \
|
||||
--encoder-model-filename $repo/exp/encoder-epoch-20-avg-1-chunk-16-left-128.int8.onnx \
|
||||
--decoder-model-filename $repo/exp/decoder-epoch-20-avg-1-chunk-16-left-128.onnx \
|
||||
--joiner-model-filename $repo/exp/joiner-epoch-20-avg-1-chunk-16-left-128.int8.onnx \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
$repo/test_wavs/DEV_T0000000000.wav
|
||||
|
||||
log "Upload onnx transducer models to huggingface"
|
||||
|
||||
url=https://huggingface.co/k2-fsa/sherpa-onnx-streaming-zipformer-multi-zh-hans-2023-12-12
|
||||
GIT_LFS_SKIP_SMUDGE=1 git clone $url
|
||||
dst=$(basename $url)
|
||||
cp -v $repo/exp/encoder*.onnx $dst
|
||||
cp -v $repo/exp/decoder*.onnx $dst
|
||||
cp -v $repo/exp/joiner*.onnx $dst
|
||||
cp -v $repo/data/lang_bpe_2000/tokens.txt $dst
|
||||
cp -v $repo/data/lang_bpe_2000/bpe.model $dst
|
||||
mkdir -p $dst/test_wavs
|
||||
cp -v $repo/test_wavs/*.wav $dst/test_wavs
|
||||
cd $dst
|
||||
git lfs track "*.onnx" bpe.model
|
||||
git add .
|
||||
git commit -m "upload model" && git push https://k2-fsa:${HF_TOKEN}@huggingface.co/k2-fsa/$dst main || true
|
||||
|
||||
log "Upload models to https://github.com/k2-fsa/sherpa-onnx"
|
||||
rm -rf .git
|
||||
rm -fv .gitattributes
|
||||
cd ..
|
||||
tar cjfv $dst.tar.bz2 $dst
|
||||
ls -lh *.tar.bz2
|
||||
mv -v $dst.tar.bz2 ../../../
|
||||
210
.github/scripts/multi_zh-hans/ASR/run.sh
vendored
Executable file
210
.github/scripts/multi_zh-hans/ASR/run.sh
vendored
Executable file
@ -0,0 +1,210 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
set -ex
|
||||
|
||||
git config --global user.name "k2-fsa"
|
||||
git config --global user.email "csukuangfj@gmail.com"
|
||||
git config --global lfs.allowincompletepush true
|
||||
|
||||
log() {
|
||||
# This function is from espnet
|
||||
local fname=${BASH_SOURCE[1]##*/}
|
||||
echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
|
||||
}
|
||||
|
||||
cd egs/multi_zh-hans/ASR
|
||||
|
||||
log "pwd: $PWD"
|
||||
|
||||
function run_2023_9_2() {
|
||||
repo_url=https://huggingface.co/zrjin/icefall-asr-multi-zh-hans-zipformer-2023-9-2
|
||||
log "Downloading pre-trained model from $repo_url"
|
||||
GIT_LFS_SKIP_SMUDGE=1 git clone $repo_url
|
||||
repo=$(basename $repo_url)
|
||||
pushd $repo
|
||||
cd exp
|
||||
git lfs pull --include pretrained.pt
|
||||
ln -s pretrained.pt epoch-99.pt
|
||||
cd ../data/lang_bpe_2000
|
||||
ls -lh
|
||||
git lfs pull --include L.pt L_disambig.pt Linv.pt bpe.model
|
||||
git lfs pull --include "*.model"
|
||||
ls -lh
|
||||
popd
|
||||
|
||||
log "--------------------------------------------"
|
||||
log "Export non-streaming ONNX transducer models "
|
||||
log "--------------------------------------------"
|
||||
./zipformer/export-onnx.py \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
--use-averaged-model 0 \
|
||||
--epoch 99 \
|
||||
--avg 1 \
|
||||
--exp-dir $repo/exp \
|
||||
--causal False
|
||||
|
||||
ls -lh $repo/exp
|
||||
|
||||
./zipformer/onnx_pretrained.py \
|
||||
--encoder-model-filename $repo/exp/encoder-epoch-99-avg-1.onnx \
|
||||
--decoder-model-filename $repo/exp/decoder-epoch-99-avg-1.onnx \
|
||||
--joiner-model-filename $repo/exp/joiner-epoch-99-avg-1.onnx \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
$repo/test_wavs/DEV_T0000000000.wav \
|
||||
$repo/test_wavs/DEV_T0000000001.wav \
|
||||
$repo/test_wavs/DEV_T0000000002.wav \
|
||||
$repo/test_wavs/TEST_MEETING_T0000000113.wav \
|
||||
$repo/test_wavs/TEST_MEETING_T0000000219.wav \
|
||||
$repo/test_wavs/TEST_MEETING_T0000000351.wav
|
||||
|
||||
rm -rf $repo
|
||||
}
|
||||
|
||||
function run_2023_11_05_streaming() {
|
||||
repo_url=https://huggingface.co/zrjin/icefall-asr-multi-zh-hans-zipformer-ctc-streaming-2023-11-05
|
||||
log "Downloading pre-trained model from $repo_url"
|
||||
GIT_LFS_SKIP_SMUDGE=1 git clone $repo_url
|
||||
repo=$(basename $repo_url)
|
||||
|
||||
pushd $repo
|
||||
cd exp/
|
||||
git lfs pull --include pretrained.pt
|
||||
rm -fv epoch-20.pt
|
||||
rm -fv *.onnx
|
||||
ln -s pretrained.pt epoch-20.pt
|
||||
cd ../data/lang_bpe_2000
|
||||
ls -lh
|
||||
git lfs pull --include L.pt L_disambig.pt Linv.pt bpe.model
|
||||
git lfs pull --include "*.model"
|
||||
ls -lh
|
||||
popd
|
||||
|
||||
log "----------------------------------------"
|
||||
log "Export streaming ONNX CTC models "
|
||||
log "----------------------------------------"
|
||||
./zipformer/export-onnx-streaming-ctc.py \
|
||||
--exp-dir $repo/exp \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
--causal 1 \
|
||||
--avg 1 \
|
||||
--epoch 20 \
|
||||
--use-averaged-model 0 \
|
||||
--chunk-size 16 \
|
||||
--left-context-frames 128 \
|
||||
--use-ctc 1
|
||||
|
||||
ls -lh $repo/exp/
|
||||
|
||||
log "------------------------------------------------------------"
|
||||
log "Test exported streaming ONNX CTC models (greedy search) "
|
||||
log "------------------------------------------------------------"
|
||||
|
||||
test_wavs=(
|
||||
DEV_T0000000000.wav
|
||||
DEV_T0000000001.wav
|
||||
DEV_T0000000002.wav
|
||||
TEST_MEETING_T0000000113.wav
|
||||
TEST_MEETING_T0000000219.wav
|
||||
TEST_MEETING_T0000000351.wav
|
||||
)
|
||||
|
||||
for w in ${test_wavs[@]}; do
|
||||
./zipformer/onnx_pretrained-streaming-ctc.py \
|
||||
--model-filename $repo/exp/ctc-epoch-20-avg-1-chunk-16-left-128.int8.onnx \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
$repo/test_wavs/$w
|
||||
done
|
||||
|
||||
log "Upload onnx CTC models to huggingface"
|
||||
url=https://huggingface.co/k2-fsa/sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13
|
||||
GIT_LFS_SKIP_SMUDGE=1 git clone $url
|
||||
dst=$(basename $url)
|
||||
cp -v $repo/exp/ctc*.onnx $dst
|
||||
cp -v $repo/data/lang_bpe_2000/tokens.txt $dst
|
||||
cp -v $repo/data/lang_bpe_2000/bpe.model $dst
|
||||
mkdir -p $dst/test_wavs
|
||||
cp -v $repo/test_wavs/*.wav $dst/test_wavs
|
||||
cd $dst
|
||||
git lfs track "*.onnx" "bpe.model"
|
||||
ls -lh
|
||||
file bpe.model
|
||||
git status
|
||||
git add .
|
||||
git commit -m "upload model" && git push https://k2-fsa:${HF_TOKEN}@huggingface.co/k2-fsa/$dst main || true
|
||||
|
||||
log "Upload models to https://github.com/k2-fsa/sherpa-onnx"
|
||||
rm -rf .git
|
||||
rm -fv .gitattributes
|
||||
cd ..
|
||||
tar cjfv $dst.tar.bz2 $dst
|
||||
ls -lh *.tar.bz2
|
||||
mv -v $dst.tar.bz2 ../../../
|
||||
|
||||
log "----------------------------------------"
|
||||
log "Export streaming ONNX transducer models "
|
||||
log "----------------------------------------"
|
||||
|
||||
./zipformer/export-onnx-streaming.py \
|
||||
--exp-dir $repo/exp \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
--causal 1 \
|
||||
--avg 1 \
|
||||
--epoch 20 \
|
||||
--use-averaged-model 0 \
|
||||
--chunk-size 16 \
|
||||
--left-context-frames 128 \
|
||||
--use-ctc 0
|
||||
|
||||
ls -lh $repo/exp
|
||||
|
||||
log "------------------------------------------------------------"
|
||||
log "Test exported streaming ONNX transducer models (Python code)"
|
||||
log "------------------------------------------------------------"
|
||||
|
||||
log "test fp32"
|
||||
./zipformer/onnx_pretrained-streaming.py \
|
||||
--encoder-model-filename $repo/exp/encoder-epoch-20-avg-1-chunk-16-left-128.onnx \
|
||||
--decoder-model-filename $repo/exp/decoder-epoch-20-avg-1-chunk-16-left-128.onnx \
|
||||
--joiner-model-filename $repo/exp/joiner-epoch-20-avg-1-chunk-16-left-128.onnx \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
$repo/test_wavs/DEV_T0000000000.wav
|
||||
|
||||
log "test int8"
|
||||
./zipformer/onnx_pretrained-streaming.py \
|
||||
--encoder-model-filename $repo/exp/encoder-epoch-20-avg-1-chunk-16-left-128.int8.onnx \
|
||||
--decoder-model-filename $repo/exp/decoder-epoch-20-avg-1-chunk-16-left-128.onnx \
|
||||
--joiner-model-filename $repo/exp/joiner-epoch-20-avg-1-chunk-16-left-128.int8.onnx \
|
||||
--tokens $repo/data/lang_bpe_2000/tokens.txt \
|
||||
$repo/test_wavs/DEV_T0000000000.wav
|
||||
}
|
||||
|
||||
function run_2023_12_12_streaming() {
|
||||
log "Upload onnx transducer models to huggingface"
|
||||
|
||||
url=https://huggingface.co/k2-fsa/sherpa-onnx-streaming-zipformer-multi-zh-hans-2023-12-12
|
||||
GIT_LFS_SKIP_SMUDGE=1 git clone $url
|
||||
dst=$(basename $url)
|
||||
cp -v $repo/exp/encoder*.onnx $dst
|
||||
cp -v $repo/exp/decoder*.onnx $dst
|
||||
cp -v $repo/exp/joiner*.onnx $dst
|
||||
cp -v $repo/data/lang_bpe_2000/tokens.txt $dst
|
||||
cp -v $repo/data/lang_bpe_2000/bpe.model $dst
|
||||
mkdir -p $dst/test_wavs
|
||||
cp -v $repo/test_wavs/*.wav $dst/test_wavs
|
||||
cd $dst
|
||||
git lfs track "*.onnx" bpe.model
|
||||
git add .
|
||||
git commit -m "upload model" && git push https://k2-fsa:${HF_TOKEN}@huggingface.co/k2-fsa/$dst main || true
|
||||
|
||||
log "Upload models to https://github.com/k2-fsa/sherpa-onnx"
|
||||
rm -rf .git
|
||||
rm -fv .gitattributes
|
||||
cd ..
|
||||
tar cjfv $dst.tar.bz2 $dst
|
||||
ls -lh *.tar.bz2
|
||||
mv -v $dst.tar.bz2 ../../../
|
||||
}
|
||||
|
||||
run_2023_9_2
|
||||
run_2023_11_05_streaming
|
||||
run_2023_12_12_streaming
|
||||
75
.github/workflows/multi-zh-hans.yml
vendored
75
.github/workflows/multi-zh-hans.yml
vendored
@ -15,47 +15,68 @@ permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
generate_build_matrix:
|
||||
if: github.repository_owner == 'csukuangfj' || github.repository_owner == 'k2-fsa'
|
||||
# see https://github.com/pytorch/pytorch/pull/50633
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
matrix: ${{ steps.set-matrix.outputs.matrix }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
- name: Generating build matrix
|
||||
id: set-matrix
|
||||
run: |
|
||||
# outputting for debugging purposes
|
||||
python ./.github/scripts/docker/generate_build_matrix.py --torch-version "2.0.0" --python-version "3.10"
|
||||
MATRIX=$(python ./.github/scripts/docker/generate_build_matrix.py --torch-version "2.0.0" --python-version "3.10")
|
||||
echo "::set-output name=matrix::${MATRIX}"
|
||||
multi-zh-hans:
|
||||
runs-on: ${{ matrix.os }}
|
||||
needs: generate_build_matrix
|
||||
name: py${{ matrix.python-version }} torch${{ matrix.torch-version }} v${{ matrix.version }}
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
os: [ubuntu-latest]
|
||||
python-version: [3.8]
|
||||
${{ fromJson(needs.generate_build_matrix.outputs.matrix) }}
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Setup Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v2
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
cache: 'pip'
|
||||
cache-dependency-path: '**/requirements-ci.txt'
|
||||
|
||||
- name: Install Python dependencies
|
||||
run: |
|
||||
grep -v '^#' ./requirements-ci.txt | xargs -n 1 -L 1 pip install
|
||||
pip uninstall -y protobuf
|
||||
pip install --no-binary protobuf protobuf==3.20.*
|
||||
|
||||
- name: Cache kaldifeat
|
||||
id: my-cache
|
||||
uses: actions/cache@v2
|
||||
with:
|
||||
path: |
|
||||
~/tmp/kaldifeat
|
||||
key: cache-tmp-${{ matrix.python-version }}-2023-05-22
|
||||
|
||||
- name: Install kaldifeat
|
||||
if: steps.my-cache.outputs.cache-hit != 'true'
|
||||
- name: Free space
|
||||
shell: bash
|
||||
run: |
|
||||
.github/scripts/install-kaldifeat.sh
|
||||
df -h
|
||||
rm -rf /opt/hostedtoolcache
|
||||
df -h
|
||||
echo "pwd: $PWD"
|
||||
echo "github.workspace ${{ github.workspace }}"
|
||||
|
||||
- name: Test with multi_zh-hans
|
||||
uses: addnab/docker-run-action@v3
|
||||
with:
|
||||
image: ghcr.io/${{ github.repository_owner }}/icefall:cpu-py${{ matrix.python-version }}-torch${{ matrix.torch-version }}-v${{ matrix.version }}
|
||||
options: |
|
||||
--volume ${{ github.workspace }}/:/icefall
|
||||
shell: bash
|
||||
run: |
|
||||
export PYTHONPATH=/icefall:$PYTHONPATH
|
||||
export HF_TOKEN=${{ secrets.HF_TOKEN }}
|
||||
cd /icefall
|
||||
git config --global --add safe.directory /icefall
|
||||
|
||||
.github/scripts/multi_zh-hans/ASR/run.sh
|
||||
|
||||
- name: Show models
|
||||
shell: bash
|
||||
run: |
|
||||
ls -lh *.tar.bz2
|
||||
|
||||
- name: export-model
|
||||
if: false
|
||||
shell: bash
|
||||
env:
|
||||
HF_TOKEN: ${{ secrets.HF_TOKEN }}
|
||||
|
||||
@ -136,6 +136,13 @@ def get_parser():
|
||||
help="The context size in the decoder. 1 means bigram; 2 means tri-gram",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--use-whisper-features",
|
||||
type=str2bool,
|
||||
default=False,
|
||||
help="True to use whisper features. Must match the one used in training",
|
||||
)
|
||||
|
||||
add_model_arguments(parser)
|
||||
|
||||
return parser
|
||||
@ -270,6 +277,7 @@ def export_streaming_ctc_model_onnx(
|
||||
model: OnnxModel,
|
||||
encoder_filename: str,
|
||||
opset_version: int = 11,
|
||||
use_whisper_features: bool = False,
|
||||
) -> None:
|
||||
model.encoder.__class__.forward = model.encoder.__class__.streaming_forward
|
||||
|
||||
@ -367,6 +375,10 @@ def export_streaming_ctc_model_onnx(
|
||||
"value_head_dims": value_head_dims,
|
||||
"num_heads": num_heads,
|
||||
}
|
||||
|
||||
if use_whisper_features:
|
||||
meta_data["feature"] = "whisper"
|
||||
|
||||
logging.info(f"meta_data: {meta_data}")
|
||||
|
||||
for i in range(len(init_state[:-2]) // 6):
|
||||
@ -547,6 +559,7 @@ def main():
|
||||
model,
|
||||
model_filename,
|
||||
opset_version=opset_version,
|
||||
use_whisper_features=params.use_whisper_features,
|
||||
)
|
||||
logging.info(f"Exported model to {model_filename}")
|
||||
|
||||
|
||||
@ -162,6 +162,13 @@ def get_parser():
|
||||
help="Whether to export models in fp16",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--use-whisper-features",
|
||||
type=str2bool,
|
||||
default=False,
|
||||
help="True to use whisper features. Must match the one used in training",
|
||||
)
|
||||
|
||||
add_model_arguments(parser)
|
||||
|
||||
return parser
|
||||
@ -342,6 +349,7 @@ def export_encoder_model_onnx(
|
||||
encoder_filename: str,
|
||||
opset_version: int = 11,
|
||||
feature_dim: int = 80,
|
||||
use_whisper_features: bool = False,
|
||||
) -> None:
|
||||
encoder_model.encoder.__class__.forward = (
|
||||
encoder_model.encoder.__class__.streaming_forward
|
||||
@ -441,6 +449,9 @@ def export_encoder_model_onnx(
|
||||
"value_head_dims": value_head_dims,
|
||||
"num_heads": num_heads,
|
||||
}
|
||||
if use_whisper_features:
|
||||
meta_data["feature"] = "whisper"
|
||||
|
||||
logging.info(f"meta_data: {meta_data}")
|
||||
|
||||
for i in range(len(init_state[:-2]) // 6):
|
||||
@ -734,6 +745,7 @@ def main():
|
||||
encoder_filename,
|
||||
opset_version=opset_version,
|
||||
feature_dim=params.feature_dim,
|
||||
use_whisper_features=params.use_whisper_features,
|
||||
)
|
||||
logging.info(f"Exported encoder to {encoder_filename}")
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user