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
decoding
游雁5079d5459560
diff --git a/funasr/models/llm_asr/model.py b/funasr/models/llm_asr/model.pyindex 14837b936..2eea19b2e 100644--- a/funasr/models/llm_asr/model.py+++ b/funasr/models/llm_asr/model.py@@ -526,7 +526,7 @@ class LLMASR2(nn.Module):]labels_ids[labels_ids == -1] = -100-+ attention_mask[attention_mask < 0] = 0model_outputs = self.llm(inputs_embeds=inputs_embeds, attention_mask=attention_mask, labels=labels_ids)