speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #1001 from alibaba-damo-academy/dev_lhn

Browse Source 
Dev lhn
This commit is contained in:
hnluo 2023-10-11 17:20:49 +08:00 committed by GitHub
commit 20ffa0e241
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.github/workflows/main.yml vendored
View File

@ -23,7 +23,7 @@ jobs:
pre-build-command: "pip install sphinx-markdown-tables nbsphinx jinja2 recommonmark sphinx_rtd_theme myst-parser"
- name: deploy copy
if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev_wjm' || github.ref == 'refs/heads/dev_lyh'
if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev_wjm' || github.ref == 'refs/heads/dev_lyh' || github.ref == 'refs/heads/dev_lhn'
run: |
mkdir public
touch public/.nojekyll
@ -35,7 +35,7 @@ jobs:
cp -r docs/m2met2/_build/html/* public/m2met2/
- name: deploy github.io pages
if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev_wjm' || github.ref == 'refs/heads/dev_lyh'
if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev_wjm' || github.ref == 'refs/heads/dev_lyh' || github.ref == 'refs/heads/dev_lhn'
uses: peaceiris/actions-gh-pages@v2.3.1
env:
GITHUB_TOKEN: ${{ secrets.ACCESS_TOKEN }}

4
funasr/datasets/large_datasets/dataset.py
View File

@ -108,7 +108,7 @@ class AudioDataset(IterableDataset):
ark_reader = ReadHelper('ark:{}'.format(data_file))
reader_list.append(ark_reader)
elif data_type == "text" or data_type == "sound" or data_type == 'text_hotword':
text_reader = open(data_file, "r")
text_reader = open(data_file, "r", encoding="utf-8")
reader_list.append(text_reader)
elif data_type == "none":
continue
@ -205,7 +205,7 @@ def Dataset(data_list_file,
# pre_prob = conf.get("pre_prob", 0) # unused yet
if pre_hwfile is not None:
pre_hwlist = []
with open(pre_hwfile, 'r') as fin:
with open(pre_hwfile, 'r', encoding="utf-8") as fin:
for line in fin.readlines():
pre_hwlist.append(line.strip())
else: