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
llm
游雁b2ea4424a3b2
diff --git a/funasr/models/paraformer/model.py b/funasr/models/paraformer/model.pyindex 729b8f500..90ce162d4 100644--- a/funasr/models/paraformer/model.py+++ b/funasr/models/paraformer/model.py@@ -455,7 +455,9 @@ class Paraformer(torch.nn.Module):speech, speech_lengths = data_in, data_lengthsif len(speech.shape) < 3:speech = speech[None, :, :]- if speech_lengths is None:+ if speech_lengths is not None:+ speech_lengths = speech_lengths.squeeze(-1)+ else:speech_lengths = speech.shape[1]else:# extract fbank feats