SenseVoice模型在funasr-1.2.0版本下，加入参数output_timestamp=True后某些音频推理报错。

[zaczou]

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

SenseVoice模型在funasr-1.2.0版本下，加入参数output_timestamp=True后某些音频推理报错。

Before asking:

1. search the issues.
2. search the docs.

What is your question?

加入参数output_timestamp=True后这条音频推理报错

Code

from funasr import AutoModel
model = AutoModel(model="/models/SenseVoiceSmall",
                  punc_model="/models/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
                  vad_model="/models/speech_fsmn_vad_zh-cn-16k-common-pytorch",
                  vad_kwargs={"max_single_segment_time": 30000},
                  disable_update=True,
                  device="cuda:0")

res = model.generate(
    input="asr_speaker_demo",
    cache={},
    language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    output_timestamp=True,
    return_raw_text=True,
)
print(res)

asr_speaker_demo.zip

What have you tried?

What's your environment?

• OS (e.g., Linux):Linux
• FunASR Version (e.g., 1.0.0): 1.2.0
• ModelScope Version (e.g., 1.11.0):1.17.1
• PyTorch Version (e.g., 2.0.0):2.1.2
• How you installed funasr (pip, source):pip
• Python version:3.9.13
• GPU (e.g., V100M32)：2080
• CUDA/cuDNN version (e.g., cuda11.7):12.1
• Docker version (e.g., funasr-runtime-sdk-cpu-0.4.1)
• Any other relevant information: