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 speaker infer
shixian.shi9285e7d5998e
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.pyindex ca6189dd2..21d8e1dd1 100644--- a/funasr/auto/auto_model.py+++ b/funasr/auto/auto_model.py@@ -6,6 +6,7 @@ import randomimport stringimport loggingimport os.path+import numpy as npfrom tqdm import tqdmfrom omegaconf import DictConfig, OmegaConf, ListConfig@@ -334,7 +335,7 @@ class AutoModel:for _b in range(len(speech_j)):vad_segments = [[sorted_data[beg_idx:end_idx][_b][0][0]/1000.0,sorted_data[beg_idx:end_idx][_b][0][1]/1000.0,- speech_j[_b]]]+ np.array(speech_j[_b])]]segments = sv_chunk(vad_segments)all_segments.extend(segments)speech_b = [i[2] for i in segments]