Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

test(tokenizer): run empty-symbol regressions in NumPy CI

zhifu gaoa6516ae40d53
diff --git a/.github/workflows/test-numpy-compatibility.yml b/.github/workflows/test-numpy-compatibility.yml
index bb5ba166e..962f78ef3 100644
--- a/.github/workflows/test-numpy-compatibility.yml
+++ b/.github/workflows/test-numpy-compatibility.yml
@@ -9,6 +9,9 @@ on:
- "tests/test_cli.py"
- "funasr/auto/auto_model.py"
- "funasr/tokenizer/sentencepiece_tokenizer.py"
+ - "funasr/tokenizer/char_tokenizer.py"
+ - "funasr/tokenizer/phoneme_tokenizer.py"
+ - "tests/test_char_tokenizer_non_linguistic_symbols.py"
- "tests/test_sentencepiece_tokenizer.py"
- "tests/test_speaker_optional_dependency.py"
- "funasr/utils/load_utils.py"
@@ -48,6 +51,9 @@ on:
- "tests/test_cli.py"
- "funasr/auto/auto_model.py"
- "funasr/tokenizer/sentencepiece_tokenizer.py"
+ - "funasr/tokenizer/char_tokenizer.py"
+ - "funasr/tokenizer/phoneme_tokenizer.py"
+ - "tests/test_char_tokenizer_non_linguistic_symbols.py"
- "tests/test_sentencepiece_tokenizer.py"
- "tests/test_speaker_optional_dependency.py"
- "funasr/utils/load_utils.py"
@@ -130,6 +136,7 @@ jobs:
tests/test_pypi_metadata.py \
tests/test_sensevoice_word_timestamps.py \
tests/test_sentencepiece_tokenizer.py \
+ tests/test_char_tokenizer_non_linguistic_symbols.py \
tests/test_pcm_input_format.py \
tests/test_realtime_ws_service.py \
tests/test_realtime_ws_hf_overrides.py \