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
fix bytes
游雁92586a4a9064
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.pyindex 9613d1b39..52753c4e2 100644--- a/funasr/utils/load_utils.py+++ b/funasr/utils/load_utils.py@@ -138,7 +138,10 @@ def load_audio_text_image_video(def load_bytes(input):- # input = validate_frame_rate(input)+ try:+ input = validate_frame_rate(input)+ except:+ passmiddle_data = np.frombuffer(input, dtype=np.int16)middle_data = np.asarray(middle_data)if middle_data.dtype.kind not in "iu":