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
Dev gzf train (#1524)
zhifu gaocd001acf68f1
diff --git a/funasr/models/paraformer/decoder.py b/funasr/models/paraformer/decoder.pyindex f08e97b3a..b75d21dbd 100644--- a/funasr/models/paraformer/decoder.py+++ b/funasr/models/paraformer/decoder.py@@ -351,9 +351,9 @@ class ParaformerSANMDecoder(BaseTransformerDecoder):hlens: torch.Tensor,ys_in_pad: torch.Tensor,ys_in_lens: torch.Tensor,- return_hidden: bool = False,- return_both: bool= False,chunk_mask: torch.Tensor = None,+ return_hidden: bool = False,+ return_both: bool = False,) -> Tuple[torch.Tensor, torch.Tensor]:"""Forward decoder.diff --git a/funasr/utils/misc.py b/funasr/utils/misc.pyindex ef18a6146..4b58d8710 100644--- a/funasr/utils/misc.py+++ b/funasr/utils/misc.py@@ -1,6 +1,7 @@import osimport ioimport shutil+import loggingfrom collections import OrderedDictimport numpy as npfrom omegaconf import DictConfig, OmegaConf