Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

fix bytes

游雁92586a4a9064
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index 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:
+ pass
middle_data = np.frombuffer(input, dtype=np.int16)
middle_data = np.asarray(middle_data)
if middle_data.dtype.kind not in "iu":