Skip to content

Fix #2815: AutoModel中，vad影响punc。 #2816

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

Open
danielalanbates wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix #2815: AutoModel中，vad影响punc。 #2816

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
12 changes: 11 additions & 1 deletion funasr/auto/auto_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -321,9 +321,19 @@ def __call__(self, *args, **cfg):
def generate(self, input, input_len=None, progress_callback=None, **cfg):
self._reset_runtime_configs()
if self.vad_model is None:
return self.inference(
results = self.inference(
input, input_len=input_len, progress_callback=progress_callback, **cfg
)
if self.punc_model is not None:
deep_update(self.punc_kwargs, cfg)
for result in results:
punc_res = self.inference(
result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg
)
if cfg.get("return_raw_text", self.kwargs.get("return_raw_text", False)):
result["raw_text"] = copy.copy(result["text"])
result["text"] = punc_res[0]["text"]
Comment on lines +328 to +335
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Feb 21, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Applying punctuation sequentially in a loop is inefficient when multiple results are present (e.g., during batch inference). The inference method supports list inputs, so you can batch all texts together for a single punctuation model call. Additionally, copy.copy() is redundant for strings as they are immutable in Python.

Suggested change
deep_update(self.punc_kwargs, cfg)
for result in results:
punc_res = self.inference(
result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg
)
if cfg.get("return_raw_text", self.kwargs.get("return_raw_text", False)):
result["raw_text"] = copy.copy(result["text"])
result["text"] = punc_res[0]["text"]
deep_update(self.punc_kwargs, cfg)
punc_results = self.inference(
[r["text"] for r in results], model=self.punc_model, kwargs=self.punc_kwargs, **cfg
)
for result, punc_res in zip(results, punc_results):
if cfg.get("return_raw_text", self.kwargs.get("return_raw_text", False)):
result["raw_text"] = result["text"]
result["text"] = punc_res["text"]

return results

else:
return self.inference_with_vad(
Expand Down