FunASR icon indicating copy to clipboard operation
FunASR copied to clipboard

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Results 484 FunASR issues
Sort by recently updated
recently updated
newest added

FunASR的维护者们,你们好。 我今天刚刚接触FunASR,并对“FunASR实时语音听写"进行安装,但失败了。 在docker容器内部,FunASR服务始终没有正常开始。并一直在进行重启: 我做过多种尝试,包括安装ffmpeg、更新funasr,但没有效果。 这是什么原因造成的?我应该怎么解决呢? 相关配置: 电脑:mac/Apple M1 Pro-芯片/系统版本-13.5 docker版本:20.10.12

bug

How does the diarization and DER% compare to that of pyannote? Thank you!

question

# 0. 微调结束后报错没有找到对应文件 报错信息如下: ![Image](https://github.com/user-attachments/assets/38047897-855b-43ae-b6d4-0b0f20166b3e) # 1. 生成的model.pt文件和model.pt.best文件比原始模型大很多 训练结束后没有生成model.pt.avg模型文件 请问上面这些问题有大佬们知道如何解决吗?

bug

First, thank you for sharing this project with us! The project's code appears to be under the MIT license per the [`README.md`](https://github.com/modelscope/FunASR/blob/d43d0853dcf3a1db04302c7b527e92ace3ccfb55/README.md?plain=1#L358-L359): https://github.com/modelscope/FunASR/blob/d43d0853dcf3a1db04302c7b527e92ace3ccfb55/README.md?plain=1#L358-L359 The repo already has a `MODEL_LICENSE` file...

documentation

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...

question

可以将仓库里面的预训练的模型转为ggml格式在whisper中使用吗?

question

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 初始化1次模型后,连续识别两个文件,连个文件都是1个多小时的音频文件,大小都是100M左右。第一个看服务器监控比较正常也会走gpu,一个多小时的录音大概2分多钟能转写完。第二个看服务器监控就基本全部走的cpu了,大概要20分钟才能转写完。 ### 代码: `import json from datetime import datetime from...

question

安装过程 1. 运行pip3 install -e ./时 2. 报错:说cmake版本过低 Preparing metadata (setup.py) ... error error: subprocess-exited-with-error × python setup.py egg_info did not run successfully. │ exit code: 1 ╰─> [37 lines...

bug

打算使用FunASR,运行UniASR实时模型【iic/speech_UniASR_asr_2pass-zh-cn-16k-audio_and_video-vocab3445-online】 [UniASR魔塔官方帖子](https://www.modelscope.cn/models/iic/speech_UniASR_asr_2pass-zh-cn-16k-audio_and_video-vocab3445-online/summary) ## ❓ Questions and Help ### Before asking: 1. search the issues. (没有相关issues) 2. search the docs. (查过没解决) 查看到只能用funasr0.8.8和modescope1.10.0仍没法使用 尝试解决依赖包版本冲突,查过对应时间的历史版本,仍报错: RuntimeError: Failed to import transformers.modeling_utils because of the...

question

您好,麻烦问您一下同样是音频转文本,C++比python代码快很多吗,自己测试下来感觉没太多提升呢

question