KeyError: 'FunASRPipeline: KeyError("GenericFunASR: \'config\'")'

[suzhaoxi]

❓ Questions and Help

运行时，提示：KeyError: 'FunASRPipeline: KeyError("GenericFunASR: \'config\'")'

What is your question?

Code

from modelscope.pipelines import pipeline from modelscope.utils.constant import Tasks

AudioFile = 'D:/project/Paraformer/data/output.wav'

inference_pipeline = pipeline( task=Tasks.auto_speech_recognition, model='damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch', model_revision="v2.0.4")

rec_result = inference_pipeline(audio_in=AudioFile)

print(rec_result)

What have you tried?

What's your environment?

• OS (Windows11):
• FunASR Version (1.0.14):
• ModelScope Version (1.11.1):
• PyTorch Version (2.2.1):
• How you installed funasr (pip):
• Python version: 3.9.17
• GPU (RTX4060)
• CUDA/cuDNN version (CUDA 12.3.104 driver):
• Docker version (null)
• Any other relevant information:

[LauraGPT]

Please update modelscope and retry it again: pip install -U modelscope

Or you could use it directly by AutoModel: https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/industrial_data_pretraining/bicif_paraformer/demo.py