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
update
shixian.shi9a27d02b7804
diff --git a/funasr/models/seaco_paraformer/model.py b/funasr/models/seaco_paraformer/model.pyindex e3cedb474..a021fe02c 100644--- a/funasr/models/seaco_paraformer/model.py+++ b/funasr/models/seaco_paraformer/model.py@@ -415,7 +415,7 @@ class SeacoParaformer(BiCifParaformer, Paraformer):token, timestamp)result_i = {"key": key[i], "text": text_postprocessed,- "timestamp": time_stamp_postprocessed,+ "timestamp": time_stamp_postprocessed, "raw_text": text}if ibest_writer is not None: