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
update
游雁9fb473bc89f6
diff --git a/funasr/models/llm_asr/model.py b/funasr/models/llm_asr/model.pyindex 937c8e1bf..2b6db96b8 100644--- a/funasr/models/llm_asr/model.py+++ b/funasr/models/llm_asr/model.py@@ -216,8 +216,8 @@ class LLMASRNAR(nn.Module):self, speech: torch.Tensor, speech_lengths: torch.Tensor, **kwargs,) -> Tuple[torch.Tensor, torch.Tensor]:- audio_mask = kwargs.get("audio_mask")- audio_token_lengths = audio_mask.sum(-1) if audio_mask else None+ audio_mask = kwargs.get("audio_mask", None)+ audio_token_lengths = audio_mask.sum(-1) if audio_mask is not None else Nonebatch = {"speech": speech, "speech_lengths": speech_lengths}enc, enc_lens = self.audio_encoder.encode(**batch)