FunASR

FunASR copied to clipboard

docker gpu 镜像，使用 iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch 模型时导出报错

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 使用funasr-gpu的docker 版本，model_dir 设置 iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch 时运行，导出 ### To Reproduce Steps to reproduce the...

yunyiaichong

代码 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++", )...

JasonChao-yue

以下代码中： ` elif not hotword_list_or_file.endswith(".txt"): logging.info("Attempting to parse hotwords as str...") hotword_list = [] hotword_str_list = [] for hw in hotword_list_or_file.strip().split(): hotword_str_list.append(hw) hw_list = hw.strip().split() if seg_dict is not None:...

darcyOly999

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 https://github.com/modelscope/FunASR/blob/main/runtime/onnxruntime/src/paraformer-online.cpp#L160-L171 在这段代码中，reserve_waveforms_的作用是什么，似乎并未参与特征的运算，是否有存在的必要 ### Before asking: 1. search the issues. 2....

CaptainNeil

Paper: https://arxiv.org/pdf/2310.11230 reference code: https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/zipformer

tiandiweizun

websocket python客户端funasr_wss_client.py上传会导致识别结果出错。

1

测试音频： https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_speaker_demo.wav 重现步骤： ``` docker pull \ registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.4.6 mkdir -p ./funasr-runtime-resources/models docker run -p 10095:10095 -it --privileged=true \ -v $PWD/funasr-runtime-resources/models:/workspace/models \ registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.4.6 #docker启动之后，进入到docker里边启动docker启动之后，进入到docker里边启动 cd FunASR/runtime nohup bash run_server.sh --download-model-dir /workspace/models...

huangxiangdan

自建数据微调 seaco_paraformer 后，推理官方音频，预测器为什么只输出开始字符？

12

###Question 微调后推理任何音频，模型都输出开始字符，最后结果输出为空，没有任何汉字。总感觉不像是微调过，而像从0训练了一遍模型，现在微调后的模型性能下降到几乎为0。微调过程如下，不知道哪一步有问题，或者我该怎么排查问题的位置呢？ ### Date {"key": "L4M8jW8rcQojNksDHH9F", "source": "/root/scx/yuyin/FunASR/data/train_audio_split/L4M8jW8rcQojNksDHH9F.wav", "source_len": 174, "target": "资料柜我不要的资料柜吗", "target_len": 11} {"key": "SAcVKMe4sYoUWG7lnTKB", "source": "/root/scx/yuyin/FunASR/data/train_audio_split/SAcVKMe4sYoUWG7lnTKB.wav", "source_len": 346, "target": "那是放资料呀我们这个不是资料柜呀", "target_len": 16} {"key": "TQSpIHjfVSIwJRf7DoAP", "source": "/root/scx/yuyin/FunASR/data/train_audio_split/TQSpIHjfVSIwJRf7DoAP.wav", "source_len": 107,...

shan2gao2shui2chang

I am attempting to fix the issue described in: #2237. When the language model (lm) is set to "none", certain Automatic Speech Recognition (ASR) tasks for.wav files are being processed...

majic31

msvc 2022 编译FunASR c++报错

1

编译环境： - Windows 10 - MSVC 2022 文件：ct-transformer-online.cpp ``` if ((strText.size() > 0 and !(strText[strText.size()-1] & 0x80)) && (strlen(sz_input) > 0 && !(sz_input[0] & 0x80))) strText += " "; ```...

patui

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 ### Before asking: 1. search the issues. 2. search the...

1xuanxia