FunASR

FunASR copied to clipboard

inference was killed due to memory(100GB was used)

2

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...

yht4work

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） 我的需求是对rtmp的直播流进行语言识别，但是在识别结果中发现，识别结果中的时间戳和保存下来的视频的时间戳对应不上，并且差距会随时间而增加。 这是测试中最后一个字的时间戳：[147610,147720] 但是保存下来的视频才2m1s，转换下就是121000左右，但是最后一个字到了147s。 ## 🐛 Bug ### To Reproduce Steps to reproduce the behavior (**always...

yuWorm

Hello Persian model https://modelscope.cn/models/iic/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/ version 1.0.1 uses some kind of roman letters in the output. It is not clear how to turn them back to unicode. Please suggest. Older version...

nshmyrev

我用的是docker funasr 4.6 cpu offline版本 模型参数都是默认的 我发送的数据为 {"mode":"offline","wav_name":"test.aac","is_speaking":true,"hotwords":"","wav_format":"aac"} 我的并发数据是10， 然后就运行一段时间报以下错误， 然后funasr-wss-server.cpp就自动重启了 Format flac detected only with low score of 13, misdetection possible! [flac @ 0x74e28c0f1300] Could not find codec parameters...

dfengpo

离线GPU版本镜像报错

2

问题: 镜像版本:funasr-runtime-sdk-gpu-0.1.1 部署了GPU版本的离线语音识别,任务跑着跑着会报错挂掉,辛苦帮忙看下,下面是报错的详细信息 报错: [aac @ 0x7f7ed01e73c0] invalid band type [aac @ 0x7f7ed01e73c0] invalid band type [aac @ 0x7f7ed01e73c0] Number of bands (54) exceeds limit (42). [mpegts @ 0x7f7ed02cb580] Packet...

ZTFsmart

I got the following model composition for English audio speech recognition with speaker classification ``` funasr_model = AutoModel(model="iic/speech_paraformer_asr-en-16k-vocab4199-pytorch", vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch", punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch", spk_model="damo/speech_campplus_sv_zh-cn_16k-common", ) ``` And I meet following questions: 1. There...

ruifengma

ubuntu系统启动离线GPU版本镜像, registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.1 使用FunASR/runtime/run_server.sh脚本, 指定 gpu bash ./run_server.sh 时报错， 请问需要如何处理 [W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema: aten::pad(Tensor self, int[] pad, str mode="constant", float? value=None) -> (Tensor) %input.827 : Float(*, *, *,...

corey1202

有大佬能帮我解释一下为什么同样的音频识别多次每次的结果都有差异吗

1

有大佬能帮我解释一下为什么同样的音频识别多次每次的结果都有差异吗

HHUhujiaxin

服务器用docker运行发生异常

2

我有一个音频文件，识别的时候就发生崩溃。 coredump内容如下： Using host libthread_db library "/lib/x86_64-linux-gnu/libthread_db.so.1". Core was generated by `/workspace/FunASR/runtime/websocket/build/bin/funasr-wss-server --download-mode'. Program terminated with signal SIGSEGV, Segmentation fault. #0 0x00007f08ce745a17 in funasr::PostProcess(std::vector&, std::vector&) () from /workspace/FunASR/runtime/websocket/build/src/libfunasr.so [Current thread...

randsoy

A10卡GPU推理效率和CPU持平，不清楚是什么地方的问题

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） ## ❓ Questions and Help ### Before asking: 1. search the issues. 2. search the...

lanyuer