mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-10 10:32:17 +00:00
* Init commit for recipes trained on multiple zh datasets. * fbank extraction for thchs30 * added support for aishell1 * added support for aishell-2 * fixes * fixes * fixes * added support for stcmds and primewords * fixes * added support for magicdata script for fbank computation not done yet * added script for magicdata fbank computation * file permission fixed * updated for the wenetspeech recipe * updated * Update preprocess_kespeech.py * updated * updated * updated * updated * file permission fixed * updated paths * fixes * added support for kespeech dev/test set fbank computation * fixes for file permission * refined support for KeSpeech * added scripts for BPE model training * updated * init commit for the multi_zh-cn zipformer recipe * disable speed perturbation by default * updated * updated * added necessary files for the zipformer recipe * removed redundant wenetspeech M and S sets * updates for multi dataset decoding * refined * formatting issues fixed * updated * minor fixes * this commit finalize the recipe (hopefully) * fixed formatting issues * minor fixes * updated * using soft links to reduce redundancy * minor updates * using soft links to reduce redundancy * minor updates * minor updates * using soft links to reduce redundancy * minor updates * Update README.md * minor updates * Update egs/multi_zh-hans/ASR/local/compute_fbank_magicdata.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/compute_fbank_magicdata.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/compute_fbank_stcmds.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/compute_fbank_stcmds.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/compute_fbank_primewords.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/compute_fbank_primewords.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * minor updates * minor fixes * fixed a formatting issue * Update preprocess_kespeech.py * Update prepare.sh * Update egs/multi_zh-hans/ASR/local/compute_fbank_kespeech_splits.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/preprocess_kespeech.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * removed redundant files * symlinks added * minor updates * added CI tests for `multi_zh-hans` * minor fixes * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh --------- Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
85 lines
2.6 KiB
YAML
85 lines
2.6 KiB
YAML
# Copyright 2023 Xiaomi Corp. (author: Zengrui Jin)
|
|
|
|
# See ../../LICENSE for clarification regarding multiple authors
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
name: run-multi-zh_hans-zipformer
|
|
|
|
on:
|
|
push:
|
|
branches:
|
|
- master
|
|
pull_request:
|
|
types: [labeled]
|
|
|
|
concurrency:
|
|
group: run_multi-zh_hans_zipformer-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
run_multi-zh_hans_zipformer:
|
|
if: github.event.label.name == 'onnx' || github.event.label.name == 'ready' || github.event_name == 'push' || github.event.label.name == 'multi-zh_hans'
|
|
runs-on: ${{ matrix.os }}
|
|
strategy:
|
|
matrix:
|
|
os: [ubuntu-latest]
|
|
python-version: [3.8]
|
|
|
|
fail-fast: false
|
|
|
|
steps:
|
|
- uses: actions/checkout@v2
|
|
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'
|
|
shell: bash
|
|
run: |
|
|
.github/scripts/install-kaldifeat.sh
|
|
|
|
- name: Inference with pre-trained model
|
|
shell: bash
|
|
env:
|
|
GITHUB_EVENT_NAME: ${{ github.event_name }}
|
|
GITHUB_EVENT_LABEL_NAME: ${{ github.event.label.name }}
|
|
run: |
|
|
sudo apt-get -qq install git-lfs tree
|
|
export PYTHONPATH=$PWD:$PYTHONPATH
|
|
export PYTHONPATH=~/tmp/kaldifeat/kaldifeat/python:$PYTHONPATH
|
|
export PYTHONPATH=~/tmp/kaldifeat/build/lib:$PYTHONPATH
|
|
|
|
.github/scripts/run-multi-zh_hans-zipformer.sh
|