zhifu gao
zhifu gao
check the log of export. The `model.pt` is missing.
max_end_silence_time=100
是支持的,需要升级到最新版本,升级指令: pip install "modelscope[audio_asr]" --upgrade -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html git clone https://github.com/alibaba/FunASR.git && cd FunASR pip install --editable ./ 包括mp3在内的多种音频格式,采样率都是支持的,用户不需要关心输入音频格式,如果遇到不支持的音频,可以反馈一下,repo:https://github.com/alibaba-damo-academy/FunASR 欢迎加入funasr钉钉群沟通您遇到的问题:27215013275
如之前在funasr群里沟通,python,多进程不可以share模型,多线程可以share模型,你是开了多进程,同时模型share,所以报错了。
如之前在funasr群里沟通,python,多进程不可以share模型,多线程可以share模型,你是开了多进程,同时模型share,所以报错了。参考用法:https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
Ref to [docs](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html#how-to-infer-from-local-model-path)
1~100, but 20 is recommended
Please raise issues follow the [docs](https://github.com/alibaba-damo-academy/FunASR/issues/1073)
OK, we would support it soon
https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining/paraformer