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
docs
游雁a974a44fcd10
diff --git a/funasr/frontends/whisper_frontend.py b/funasr/frontends/whisper_frontend.pyindex acf32dbc7..1bd8aecdd 100644--- a/funasr/frontends/whisper_frontend.py+++ b/funasr/frontends/whisper_frontend.py@@ -33,7 +33,7 @@ class WhisperFrontend(nn.Module):self.win_length = N_FFTself.hop_length = HOP_LENGTHself.pad_samples = N_SAMPLES- self.frame_shift = self.hop_length+ self.frame_shift = int(self.hop_length / self.fs * 1000)self.lfr_n = 1self.n_mels = n_melsif whisper_model == "large-v3" or whisper_model == "large":