search

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
6.47k stars 688 forks source link

TypeError: 'list' object cannot be interpreted as an integer #1588

Closed lonngxiang closed 6 months ago

lonngxiang commented 6 months ago 
from funasr import AutoModel
# paraformer-zh is a multi-functional asr model
# use vad, punc, spk or not as you need
model = AutoModel(model="paraformer-zh",  vad_model="fsmn-vad",  punc_model="ct-punc", 
                  # spk_model="cam++", 
                  )
res = model.generate(input=f"{model.model_path}/example/asr_example.wav", 
                     batch_size_s=300, 
                     hotword='魔搭')
print(res)

用的这个音频 ezyzip·.zip

image

ArboterJams commented 6 months ago

是什么原因啊，我也遇到了这个问题。

R1ckShi commented 6 months ago

fixed, please pull the latest code

lonngxiang commented 6 months ago

fixed, please pull the latest code

重启pip 安装funasr吗？

R1ckShi commented 6 months ago

fixed, please pull the latest code

重启pip 安装funasr吗？

这种即时修复的问题只能通过源码安装，clone funasr仓库，pip install -e ./ pip安装的方式需要等funasr在pypi上发版才可以

lonngxiang commented 6 months ago

fixed, please pull the latest code

重启pip 安装funasr吗？

这种即时修复的问题只能通过源码安装，clone funasr仓库，pip install -e ./ pip安装的方式需要等funasr在pypi上发版才可以

好的，辛苦了