Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
fix(runtime): merge spelled-out acronyms into one word in sentence_postprocess
Tanishq1c217c524900
diff --git a/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py b/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.pyindex 3f8d9999e..34180841c 100644--- a/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py+++ b/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py@@ -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 += 1while num < words_size:if num in abbr_end:- word_lists.append(words[num].upper())+ abbr_word += words[num].upper()last_num = numbreakelse: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])diff --git a/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py b/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.pyindex 343ed383a..3a62afee6 100644--- a/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py+++ b/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py@@ -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 += 1while num < words_size:if num in abbr_end:- word_lists.append(words[num].upper())+ abbr_word += words[num].upper()last_num = numbreakelse: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])diff --git a/tests/test_sentence_postprocess_timestamps.py b/tests/test_sentence_postprocess_timestamps.pyindex 0aa6965c7..921495097 100644--- a/tests/test_sentence_postprocess_timestamps.py+++ b/tests/test_sentence_postprocess_timestamps.py@@ -96,6 +96,26 @@ class SentencePostprocessTimestampTest(unittest.TestCase):("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()