Skip to content

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

fix: Fun-ASR-Nano batch check uses actual data size instead of kwargs batch_size

游雁89ef5f7ae9df
diff --git a/funasr/models/fun_asr_nano/model.py b/funasr/models/fun_asr_nano/model.py
index a4eba71b5..a6507525d 100644
--- a/funasr/models/fun_asr_nano/model.py
+++ b/funasr/models/fun_asr_nano/model.py
@@ -469,7 +469,7 @@ class FunASRNano(nn.Module):
):
meta_data = {}
- if kwargs.get("batch_size", 1) > 1:
+ if len(data_in) > 1:
raise NotImplementedError("batch decoding is not implemented")
contents = self.data_template(data_in[0])