Skip to content

fix(fun-asr-nano): normalize ISO language hints #3613

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
Sep 2, 2026
Merged

fix(fun-asr-nano): normalize ISO language hints #3613

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
9 changes: 9 additions & 0 deletions funasr/models/fun_asr_nano/inference_vllm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,13 @@

dtype_map = {"bf16": torch.bfloat16, "fp16": torch.float16, "fp32": torch.float32}

_LANGUAGE_PROMPT_ALIASES = {
"zh": "中文",
"en": "英文",
"ja": "日文",
"ko": "韩文",
}


def _resolve_vllm_dtype(dtype: str) -> str:
"""Use a numerically stable dtype for the Qwen3 language model."""
Expand Down Expand Up @@ -462,6 +469,8 @@ def _build_prompt_text(
itn: bool = True,
) -> str:
"""Build the ASR prompt string."""
if language:
language = _LANGUAGE_PROMPT_ALIASES.get(language.lower(), language)
hotwords = hotwords or []
if len(hotwords) > 0:
hotwords_str = ", ".join(hotwords)
Expand Down
14 changes: 14 additions & 0 deletions tests/test_fun_asr_nano_vllm_prompt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
from funasr.models.fun_asr_nano.inference_vllm import FunASRNanoVLLM


def test_iso_language_aliases_use_documented_prompt_names():
model = object.__new__(FunASRNanoVLLM)

assert model._build_prompt_text(language="zh") == "语音转写成中文："
assert model._build_prompt_text(language="en") == "语音转写成英文："


def test_custom_language_prompt_is_preserved():
model = object.__new__(FunASRNanoVLLM)

assert model._build_prompt_text(language="粤语") == "语音转写成粤语："
Loading