Skip to content

fix(runtime): merge spelled-out acronyms into one word in funasr_onnx and funasr_torch sentence_postprocess #3869

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

Merged
LauraGPT merged 1 commit into from
Nov 11, 2026
+28 −6
Merged

fix(runtime): merge spelled-out acronyms into one word in funasr_onnx and funasr_torch sentence_postprocess #3869

Show file tree
Hide file tree
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
7 changes: 4 additions & 3 deletions runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,17 +106,18 @@ def abbr_dispose(words: List[Any], time_stamp: List[List] = None) -> List[Any]:
if num in abbr_begin:
if time_stamp is not None:
begin = time_stamp[ts_nums[num]][0]
word_lists.append(words[num].upper())
abbr_word = words[num].upper()
num += 1
while num < words_size:
if num in abbr_end:
word_lists.append(words[num].upper())
abbr_word += words[num].upper()
last_num = num
break
else:
if words[num].encode("utf-8").isalpha():
word_lists.append(words[num].upper())
abbr_word += words[num].upper()
num += 1
word_lists.append(abbr_word)
if time_stamp is not None:
end = time_stamp[ts_nums[num]][1]
ts_lists.append([begin, end])
Expand Down
7 changes: 4 additions & 3 deletions runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,17 +108,18 @@ def abbr_dispose(words: List[Any], time_stamp: List[List] = None) -> List[Any]:
if num in abbr_begin:
if time_stamp is not None:
begin = time_stamp[ts_nums[num]][0]
word_lists.append(words[num].upper())
abbr_word = words[num].upper()
num += 1
while num < words_size:
if num in abbr_end:
word_lists.append(words[num].upper())
abbr_word += words[num].upper()
last_num = num
break
else:
if words[num].encode("utf-8").isalpha():
word_lists.append(words[num].upper())
abbr_word += words[num].upper()
num += 1
word_lists.append(abbr_word)
if time_stamp is not None:
end = time_stamp[ts_nums[num]][1]
ts_lists.append([begin, end])
Expand Down
20 changes: 20 additions & 0 deletions tests/test_sentence_postprocess_timestamps.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,6 +96,26 @@ def test_untimed_transcription_still_accepts_filtered_tokens(self):
("你好", ["你", "好"]),
)

def test_spelled_out_letters_are_one_word_with_one_timestamp(self):
self.assert_timestamps(
["我", "用", "a", "i", "写", "代", "码"],
["我", "用", "AI", "写", "代", "码"],
[[0, 100], [100, 200], [200, 400], [400, 500], [500, 600], [600, 700]],
)
self.assert_timestamps(
["i", "b", "m", "is", "here"],
["IBM", "is", "here"],
[[0, 300], [300, 400], [400, 500]],
)

def test_spelled_out_letters_are_one_word_without_timestamps(self):
for path in POSTPROCESS_UTILS:
with self.subTest(path=path):
self.assertEqual(
_load_sentence_postprocess(path)(["看", "c", "c", "t", "v", "新", "闻"]),
("看CCTV新闻", ["看", "CCTV", "新", "闻"]),
)


if __name__ == "__main__":
unittest.main()
Loading