英文识别的原始结果不正常，还是给出的ITN结果

[Ziyi6]

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

Before asking:

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

What is your question?

英文的音频，在给定use_itn=False后，输出的识别结果还是带有数字等；中文的音频是正常的，出的都是汉字，不是数字。可以请教一下是哪里出了问题吗？
test_number_ASR_wavs.zip

use_itn=False: 'text': "<|en|><|EMO_UNKNOWN|><|Speech|><|woitn|>500 million cruise ship and to make this one hour fun i hit 100000 brainly throughout the cruise ship whatever you guys find you can keep that's your signature to run while he's looking for money i want to tell you about experience"

use_itn=True: 'text': "<|en|><|EMO_UNKNOWN|><|Speech|><|withitn|>500 million cruise ship and to make this one hour fun I hit $100,000 brainly throughout the cruise ship whatever you guys find you can keep that's your signature to run while he's looking for money, I want to tell you about experience."

Code

from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess

model_dir = "/data/Projects/models/sensevoice-small"

if __name__ == '__main__':
    model = AutoModel(model=model_dir, trust_remote_code=True, device="cuda:0")
    res = model.generate(
        # input="/data/test_numbesr_CHNwav.wav",
        input = '/data/test_numbesr_EN.wav',
        cache={},
        language="en", # "zh", "en", "yue", "ja", "ko", "nospeech"
        use_itn=False,
        batch_size=64, 
    )
    print(type(res))
    print(res)

What have you tried?

What's your environment?

Ubuntu 22.04, funasr

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

[WangFeiji0928]

所以你是想要five hundred而不是500是吗😄