关于流式语音识别模型的输出问题，请问如何解决？

[White-Friday]

Notice: In order to resolve issues more efficiently, please raise issue following the template. （注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节）

❓ Questions and Help

在使用流式模型speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online，按照modelscope上面的代码示例，语音文件更换为自己的语音，流式识别的效果很差，几乎不能使用。使用非流式的语音识别模型，效果还是很好的

Before asking:

实际小部分输出效果，text基本为空： [{'key': 'rand_key_xVktYncJB4AIv', 'text': ''}] [{'key': 'rand_key_nisfidv7diPeH', 'text': ''}] [{'key': 'rand_key_hhUdhjy389Ntb', 'text': ''}] [{'key': 'rand_key_CgmMUMGJaZoka', 'text': ''}] [{'key': 'rand_key_KCq3s4MM19l62', 'text': ''}] [{'key': 'rand_key_GMz5ugkhJjEja', 'text': ''}] [{'key': 'rand_key_MctnhqqCF5Z7o', 'text': ''}] [{'key': 'rand_key_r4RMJB5Dt9CoM', 'text': ''}] [{'key': 'rand_key_IAgAzmhVx0OPP', 'text': ''}] [{'key': 'rand_key_Kp4Q3VbGRebTA', 'text': ''}] [{'key': 'rand_key_wmTnvBgc3U5FB', 'text': ''}] [{'key': 'rand_key_3try9M9ryLjOi', 'text': ''}] [{'key': 'rand_key_belcu3MxHD1BZ', 'text': ''}] [{'key': 'rand_key_mzdwXRGyQQDKM', 'text': '是'}] 下面是代码：

from funasr import AutoModel
import soundfile
import os

chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention

model = AutoModel(
                  model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="v2.0.4"
                  #model="iic/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online", model_revision="master"
                  #vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch", vad_model_revision="v2.0.4",
                  #punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch", punc_model_revision="v2.0.4"    
                )
cache = {}

wav_file = "wavs/test2.wav"
speech, sample_rate = soundfile.read(wav_file)

chunk_stride = chunk_size[1] * 960 # 600ms、480ms

cache = {}

total_chunk_num = int(len((speech)-1)/chunk_stride+1)
for i in range(total_chunk_num):
    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
    is_final = i == total_chunk_num - 1
    res = model.generate(input=speech_chunk,
                cache=cache,
                is_final=is_final,
                chunk_size=chunk_size,
                encoder_chunk_look_back=encoder_chunk_look_back,
                decoder_chunk_look_back=decoder_chunk_look_back,
                )
    print(res)

[LauraGPT]

usesoxi to check the audio format.