modelscope / FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
https://www.funasr.com
Other
6.49k stars 688 forks source link

UnsupportedValueType: FunASRPipeline: GenericFunASR: Value 'CharTokenizer' is not a supported primitive type #1423

Closed liangpenglong closed 7 months ago

liangpenglong commented 7 months ago

❓ Questions and Help

What is your question?

遵循链接: https://www.modelscope.cn/models/iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary https://github.com/alibaba-damo-academy/FunASR#installation 进行funasr modelscope安装并尝试调用api进行推理

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

inference_pipeline = pipeline( task=Tasks.auto_speech_recognition, model='iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1', model_revision="v2.0.4")

rec_result = inference_pipeline('https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav') print(rec_result)

遇到如下错误: omegaconf.errors.UnsupportedValueType: FunASRPipeline: GenericFunASR: Value 'CharTokenizer' is not a supported primitive type full_key: tokenizer object_type=dict

Code

What have you tried?

尝试更新funasr 和modelscope版本,并未奏效,Google不到相关错误信息。

What's your environment?

LauraGPT commented 7 months ago

Sorry, bug has been fixed. https://github.com/alibaba-damo-academy/FunASR/pull/1425/files Please update funasr-1.0.13 and try it again.

daocodedao commented 7 months ago

pip install 找不到1.0.13

LauraGPT commented 7 months ago

pip install 找不到1.0.13

pip install -U funasr -i https://pypi.org/simple