Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[unit] use resource #2297

Merged
merged 1 commit into from
Jan 11, 2024
Merged

[unit] use resource #2297

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 7 additions & 21 deletions test/wenet/text/test_paraformer_tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,33 +1,19 @@
import pytest
import os
from wenet.paraformer.convert_paraformer_to_wenet_config_and_ckpt import (
extract_dict, _download_fn)
from wenet.utils.init_tokenizer import init_tokenizer

import yaml


@pytest.fixture()
@pytest.fixture(params=[[
"test/resources/paraformer.words.txt",
"test/resources/paraformer.seg_dict.txt"
]])
def paraformer_tokenizer(request):
_ = request
download_root = os.path.join(os.path.expanduser("~"), ".cache")
seg_dict = 'seg_dict'
_download_fn(download_root, seg_dict)

config_name = 'config.yaml'
_download_fn(download_root, config_name, version='v1.2.4')
with open(os.path.join(download_root, config_name), 'r') as fin:
configs = yaml.load(fin, Loader=yaml.FullLoader)
wenet_units = os.path.join(download_root, 'units.txt')
extract_dict(configs, wenet_units)

symbol_table_path, seg_dict = request.param
configs = {}
configs['model'] = 'paraformer'
configs['tokenizer'] = 'paraformer'
configs['tokenizer_conf'] = {}
configs['tokenizer_conf']['symbol_table_path'] = wenet_units
configs['tokenizer_conf']['seg_dict_path'] = os.path.join(
download_root, seg_dict)
configs['tokenizer_conf']['symbol_table_path'] = symbol_table_path
configs['tokenizer_conf']['seg_dict_path'] = seg_dict
return init_tokenizer(configs)


Expand Down
Loading