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 cif export
维石c3ec6b9b9e44
diff --git a/funasr/models/paraformer/cif_predictor.py b/funasr/models/paraformer/cif_predictor.pyindex 535131f39..24145cd33 100644--- a/funasr/models/paraformer/cif_predictor.py+++ b/funasr/models/paraformer/cif_predictor.py@@ -449,7 +449,7 @@ class CifPredictorV2Export(torch.nn.Module):mask = mask.transpose(-1, -2).float()mask = mask.squeeze(-1)hidden, alphas, token_num = self.tail_process_fn(hidden, alphas, mask=mask)- acoustic_embeds, cif_peak = cif_v1_export(hidden, alphas, self.threshold)+ acoustic_embeds, cif_peak = cif_export(hidden, alphas, self.threshold)return acoustic_embeds, token_num, alphas, cif_peak