Skip to content

Issues: modelscope/FunASR

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

226 Open 1,049 Closed
226 Open 1,049 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

dengcunqin/speech_seaco_paraformer_large_asr_nat-zh-cantonese-en-16k-common-vocab11666-pytorch获取时间戳？ bug Something isn't working
#2358 opened Jan 10, 2025 by a122760
1
训练报错 bug Something isn't working
#2357 opened Jan 10, 2025 by someoneformulated
利用example/paraformer/finetune.sh进行微调后，利用TensorBoard对训练过程可视化的过程中，怎么只能显示step为6的数据？只有train的数据，没有val的数据 question Further information is requested
#2356 opened Jan 9, 2025 by chentiejin1
run_server.sh脚本不能指定revision参数，造成按示例跑不起来8k采样离线服务 bug Something isn't working
#2355 opened Jan 9, 2025 by kirinrin
finetune.sh好像不能在windows上运行， question Further information is requested
#2353 opened Jan 6, 2025 by yjlyjl666
请问怎么把容器中的vad模型去掉？我在实时推理的shell脚本中尝试去掉vad，但是会报错 question Further information is requested
#2352 opened Jan 4, 2025 by sanwei111
在通过funasr_wss_service.py进行实时识别录音语音的过程中，如何消除TTS转发的语音，就是如何做回音消除 question Further information is requested
#2350 opened Jan 3, 2025 by chentiejin1
为什么使用本地代码推理的时候，没有lm-dir这个参数？无论是量化前还是量化后。而部署到服务器时，无论是实时还是离线，都有lm-dir这个参数？？？ question Further information is requested
#2349 opened Jan 2, 2025 by sanwei111
为什么gpu版本没有流式回复了，识别速度很慢 question Further information is requested
#2348 opened Jan 2, 2025 by worm128
gpu方式部署，run_server.sh运行时，显卡使用率低，相较于cpu提升很小 question Further information is requested
#2346 opened Jan 2, 2025 by javed119
1
怎么才能调用本地下载好的模型，而不是通过 hf 或者 ms 联网搜索？ question Further information is requested
#2345 opened Dec 31, 2024 by piwawa
请问这个模型能成功将长视频（比如10小时20小时的那种视频）转为字幕吗？ question Further information is requested
#2344 opened Dec 30, 2024 by ssszzc
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？ question Further information is requested
#2342 opened Dec 28, 2024 by shan2gao2shui2chang
7
当前代码demo_libtorch.py报错 question Further information is requested
#2341 opened Dec 27, 2024 by cbsyy
英文建模使用什么建模单元？ question Further information is requested
#2340 opened Dec 27, 2024 by a122760
Sensevoice timestamp error when process multiple VAD segments: lack index in encoder_out_lens
#2339 opened Dec 26, 2024 by njzheng
2
CHUNK_SIZE 和chunk_interval 是什么意思？ question Further information is requested
#2338 opened Dec 26, 2024 by sanwei111
连接websocket后，语音输入一段话，此时是正常的；然后不断开websocket服务，停留若干时间，再语音输入，则会报错误vad_feats's size is 0；最后如果重新建立websocket服务，则恢复正常 bug Something isn't working
#2337 opened Dec 26, 2024 by lessuit
本地推理和在线推理结果不一致，本地错误很多 question Further information is requested
#2335 opened Dec 25, 2024 by troycjj
1
SenseVoice模型在funasr-1.2.0版本下，加入参数output_timestamp=True后某些音频推理报错。 question Further information is requested
#2333 opened Dec 25, 2024 by zaczou
SenseVoice在FunASR的1.2.0版本时间戳与字符概率对不齐的问题 bug Something isn't working
#2324 opened Dec 20, 2024 by psk-github
@R1ckShi
唤醒词模型是否有 C++ onnx 支持 question Further information is requested
#2322 opened Dec 19, 2024 by endink
3
seaco-paraformer 12月份oNNX导出存在问题，回退11月4号正常 bug Something isn't working
#2320 opened Dec 19, 2024 by Yuxiang1990
@R1ckShi
如果一段音频中有停顿，需要加空格吗？比如说一个说，我，停了三秒，再说我是人。那么转录文本需要写成“我 我是人”吗？ question Further information is requested
#2319 opened Dec 18, 2024 by sanwei111
1
镜像 funasr-runtime-sdk-online-cpu-0.1.12 使用 SenseVoice 报错 bug Something isn't working
#2318 opened Dec 18, 2024 by lianzhehua
ProTip! Adding no:label will show everything without a label.