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
bug fix
维石09f0f2054596
diff --git a/funasr/utils/timestamp_tools.py b/funasr/utils/timestamp_tools.pyindex 84a02b230..3d8fd1062 100644--- a/funasr/utils/timestamp_tools.py+++ b/funasr/utils/timestamp_tools.py@@ -156,7 +156,6 @@ def timestamp_sentence(punc_id = int(punc_id) if punc_id is not None else 1sentence_end = timestamp[1] if timestamp is not None else sentence_end- sentence_start = timestamp[0] if timestamp is not None else sentence_startsentence_text_seg = (sentence_text_seg[:-1] if sentence_text_seg[-1] == " " else sentence_text_seg)@@ -184,6 +183,7 @@ def timestamp_sentence(sentence_text = ""sentence_text_seg = ""ts_list = []+ sentence_start = timestamp[0] if timestamp is not None else sentence_startreturn res