czydfj
czydfj
In Reformer, do all sentences of different lengths have to be processed to the length of 8192, and then processed through the mask?
我在试用inference的webui。为什么我每次输入一个大约100个字的文本进去，它只能返回最后一小段的语音生成结果，这个结果一定在10秒以内？
想请问一下zero shot模式下输入参考音频的时候，是否有时长的限制呢？ 我试了一下6秒的参考音频时可以很快输出结果的，但是加到12秒，它就一直卡着不动，十几分钟了。
### Self Checks - [X] I have thoroughly reviewed the project documentation (installation, training, inference) but couldn't find any relevant information that meets my needs. [English](https://speech.fish.audio/) [中文](https://speech.fish.audio/zh/) [日本語](https://speech.fish.audio/ja/) [Portuguese (Brazil)](https://speech.fish.audio/pt/)...
版本：funasr 1.2.6 模型：iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch 使用上述版本提取timestamp和文本有1个字的时间戳偏移。
when I run pip install, it seems no matching version: ERROR: Could not find a version that satisfies the requirement resemble-enhance (from versions: none) ERROR: No matching distribution found for...
Building wheel for aeneas (setup.py) ... error error: subprocess-exited-with-error × python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> [207 lines of output] running bdist_wheel running build...
I have a custom graph (including entities, relationships and chunks). I want to insert it into nano-graphrag, generate community reports, and use the query method of nano-graphrag. Is there an...