FunASR

FunASR copied to clipboard

模型微调过程中遇到了问题

4

_pickle.UnpicklingError: invalid load key, 'v'

ahengisyour88

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） ## ❓ Questions and Help linux上多次调用模型就卡住了,卡在0%或者需要很久几分钟才能出来 模型文件是这里面下载的https://modelscope.cn/models/iic/SenseVoiceSmall/files  ### Before asking: 1. search the issues....

Blue-FatMan

部署没问题，无法调用

1

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 前端无法调用，10095端口是开放的   ### To Reproduce Steps to reproduce the behavior (**always...

infoBrainSys

没有修改代码，直接部署的，但是语音实时转化为文字时报错，错误如下 language: auto, merge_vad: True 0%| | 0/1 [00:00

linlom025

I trained with finetune.sh, and the model is :"iic/SenseVoiceSmall". Training with four data: FunASR - the main/data/list/train jsonl. It's only contains two language English and Chinese. But when I test...

2833034152

## 📚 Documentation https://github.com/modelscope/FunASR/blob/main/docs/tutorial/README_zh.md，这篇文档有个错别字： 

byronv5

镜像 funasr-runtime-sdk-online-cpu-0.1.12 使用 SenseVoice 报错

5

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 用 funasr-runtime-sdk-online-cpu-0.1.12 镜像，--model-dir 指定 SenseVoiceSmall-onnx 模型，offline results 没有办法正常输出，报错如下: ``` E20241218 17:33:19.854435 372...

lianzhehua

funasr + Whisper语音识别-多语言-large-v3 + fsmn-vad + ct-punc-c + cam++ 报错 raise NotImplementedError("batch decoding is not implemented") NotImplementedError: batch decoding is not implemented

3

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） ## ❓ Questions and Help 使用funasr调用Whisper语音识别-多语言-large-v3这个模型，并使用了fsmn-vad ； ct-punc-c ；cam++，报错 错误如下： funasr version: 1.1.16. Check update...

guiniao

# 0. 训练时的tensorboard曲线如何看？ 下面是我在训练中截图的曲线。  请问我是看rank0还是rank1？ Thanks

lukeewin

paraformer微调之后模型变大，且和basemodel推理同一段wav文件时会报错

4

在对paraformer长音频版模型进行微调之后，保存的pt文件大小由basemodel的800多M增加到了近2.6G， 且在推理同一段wav文件时，会报错，报错信息如下： Traceback (most recent call last): File "/wind/aispace/train/source/src/FunASR/examples/industrial_data_pretraining/paraformer-zh-spk/tasks_bin.py", line 220, in results_left = asr_batch_infer(output_left_folder,paraformer_model) File "/wind/aispace/train/source/src/FunASR/examples/industrial_data_pretraining/paraformer-zh-spk/tasks_bin.py", line 124, in asr_batch_infer res = paraformer_model.generate(input=audio_binary,fs=8000) File "/wind/aispace/train/source/src/FunASR/funasr/auto/auto_model.py", line 300, in generate...

YouTwoMeToo