Skip to content

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

decoding

游雁7c4cfcfab4f4
diff --git a/funasr/models/llm_asr/model.py b/funasr/models/llm_asr/model.py
index 03a2c08b0..ea039a5f4 100644
--- a/funasr/models/llm_asr/model.py
+++ b/funasr/models/llm_asr/model.py
@@ -1018,7 +1018,7 @@ class LLMASR4(nn.Module):
for turn_id in range(fbank_beg.shape[1]):
fbank_beg_idx = fbank_beg[batch_idx, turn_id].item()
- if fbank_beg[batch_idx, turn_id] > 0:
+ if fbank_beg_idx > 0:
speech_token_len = fake_token_len[batch_idx, turn_id]
speech_token = encoder_out[speech_idx, :speech_token_len, :]