-
Notifications
You must be signed in to change notification settings - Fork 798
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
请问什么时候可以支持emotion2vec模型微调?
question
Further information is requested
#1520
opened Mar 21, 2024 by
wjyfelicity
Feature Request: Add emotion2vec to funasr-runtime-sdk docker image
#1571
opened Mar 30, 2024 by
markyfsun
你好请问,这个流式asr最小支持的语音帧为多少呢,其次它的采样率有没有要求,我看默认的是16khz
question
Further information is requested
#1646
opened Apr 23, 2024 by
tanggang1997
finetune训练时,内存会随着训练步数增多而增大,直到占满内存报错 Cannot allocate memory
bug
Something isn't working
#1716
opened May 10, 2024 by
JucyCherry
VAD - output speech segment probability
question
Further information is requested
#1749
opened May 22, 2024 by
bigchou
finetune时的学习率问题,经过初始lr经过scheduler后变得特别小
question
Further information is requested
#1792
opened Jun 7, 2024 by
pika-online
新闻联播音频男女主持人声音间隔1.8s CAM++ 无法区分,测试音频如下
bug
Something isn't working
#1864
opened Jul 1, 2024 by
wuhongsheng
使用 nuitka 编译的程序打包运行时出错: AssertionError: ContextualParaformer is not registered
question
Further information is requested
#1866
opened Jul 1, 2024 by
kanslor
AssertionError: cam++ is not registered on CUDA12.1
bug
Something isn't working
#1871
opened Jul 3, 2024 by
ozora-ogino
Finetube the punctuation model
question
Further information is requested
#1876
opened Jul 3, 2024 by
mark95
onnx的Paraformer类中__call__函数有一个分支无法被执行,导致返回值为空
bug
Something isn't working
#1878
opened Jul 4, 2024 by
liaoyu-qing
C++部署没有适配spk model ,希望能增加适配spk model
question
Further information is requested
#1892
opened Jul 8, 2024 by
yanglinlong6
能用AutoModel加载.onnx的模型吗
question
Further information is requested
#1938
opened Jul 22, 2024 by
viviliuwqhduhnwqihwqwudceygysjiwuwnn
如何加载多个.onnx模型,对同一个音频处理
question
Further information is requested
#1939
opened Jul 22, 2024 by
viviliuwqhduhnwqihwqwudceygysjiwuwnn
Why does the batch size significantly affect the recognition results in (iic/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020) and other models are not significantly affected by the batch size?paraformer-en长音频版对batch size(或者说padding操作)过于敏感,严重影响识别结果
bug
Something isn't working
question
Further information is requested
#1972
opened Jul 30, 2024 by
283258771
推理时RuntimeError: Expected 2D or 3D (batch mode) tensor with possibly 0 batch size and other non-zero dimensions for input, but got: [1, 0, 0]
question
Further information is requested
#1974
opened Jul 31, 2024 by
sethws
How is the FP16 model trained?
question
Further information is requested
#1985
opened Aug 5, 2024 by
icestoneking
vad model的rtf为0.831是正常的吗?
question
Further information is requested
#1987
opened Aug 5, 2024 by
nixonjin
微调iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch模型,请问大概需要多少条数据啊?我看data\list\train.jsonl里就三条数据
question
Further information is requested
#1988
opened Aug 6, 2024 by
viviliuwqhduhnwqihwqwudceygysjiwuwnn
使用pipeline进行ASR时,当输入是scp文件,进程不解除输出目录的文件占用
bug
Something isn't working
#1989
opened Aug 6, 2024 by
Simon-chai
speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common 是否支持热词
question
Further information is requested
#1999
opened Aug 9, 2024 by
dfengpo
parformer大规模数据集预训练cpu内存持续增加的问题
question
Further information is requested
#2018
opened Aug 15, 2024 by
chenpaopao
Previous Next
ProTip!
Exclude everything labeled
bug
with -label:bug.