No speech gets repeated recognition results

[ben-8543]

useing follow code to decoding in a asr server, I get repeated recognition results not related to speech.
codes:

import whisper
model = whisper.load_model("large")

# load audio and pad/trim it to fit 30 seconds
audio = whisper.load_audio("audio.mp3")
audio = whisper.pad_or_trim(audio)

# make log-Mel spectrogram and move to the same device as the model
mel = whisper.log_mel_spectrogram(audio).to(model.device)

# detect the spoken language
_, probs = model.detect_language(mel)
print(f"Detected language: {max(probs, key=probs.get)}")

# decode the audio
options = whisper.DecodingOptions()
result = whisper.decode(model, mel, options)

# print the recognized text
print(result.text)

Very sudden repeated recognition results are as follows:

"测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试测试"
"我去找他好我去找他好我去找他好我去找他好我去找他好我去找他好我去找他好我去找他好我去找他好我去找他好我去找他好我去找他好我去找他好我去找他好我去找他"
""作词 作曲 编曲 混音 母带 母带""
"整理&字幕:\"三马兄,欢迎来到汉族联合播剧场——鲍尔德亚公司!\""}
"【本期视频与您无关,请勿模仿】咋的了?【本期视频与您无关,请勿模仿】【本期视频与您无关,请勿模仿】【本期视频与您无关,请勿模仿】我找一段都没画【本期视频与您无关,请勿模仿】【本期视频与您无关,请勿模仿】【本期"
"本视频由红十字会和Skype上的合作伙伴提供】"

[wllbll]

I encounter this issue too when trying to transcript an music audio, it may get rid of this with VAD

[t880216t]

I also have this problem.