Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

llm

游雁b2ea4424a3b2
diff --git a/funasr/models/paraformer/model.py b/funasr/models/paraformer/model.py
index 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_lengths
if 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