识别pcm扩展名（16k 1c 16bit）音频，报"Failed to load audio"

[weilikai]

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）

🐛 Bug

识别PCM音频，报错"Failed to load audio"

To Reproduce

识别pcm扩展名（16k 1c 16bit）音频，报"Failed to load audio"

Code sample

import os
import requests
import json

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

model_dir = "iic/SenseVoiceSmall"

model = AutoModel(
    model=model_dir,
    vad_model="fsmn-vad",
    vad_kwargs={"max_single_segment_time": 30000},
    device="cuda:0",
)

res = model.generate(
    input="test.pcm",
    cache={},
    language="auto",  # "zn", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
    merge_length_s=15,
)
text = rich_transcription_postprocess(res[0]["text"])

Expected behavior

按照16k 1c 16bit来加载pcm扩展名的音频并正常识别

Environment

• OS: Ubuntu 22.04.3 LTS
• Python: Python 3.10.12
• FunASR: 1.2.7
• ModelScope: 1.30.0
• PyTorch: 2.8.0
• CUDA: True, Version: 12.8
• Quadro RTX 4000

Additional context