ARM架构cosyvoice2安装问题

[Caojia520Suiyng]

File "/home/caojia/item/models/CosyVoice/cosyvoice/cli/frontend.py", line 28, in import ttsfrd ModuleNotFoundError: No module named 'ttsfrd'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/caojia/item/models/CosyVoice/webui.py", line 25, in from cosyvoice.cli.cosyvoice import CosyVoice, CosyVoice2 File "/home/caojia/item/models/CosyVoice/cosyvoice/cli/cosyvoice.py", line 21, in from cosyvoice.cli.frontend import CosyVoiceFrontEnd File "/home/caojia/item/models/CosyVoice/cosyvoice/cli/frontend.py", line 32, in from tn.chinese.normalizer import Normalizer as ZhNormalizer File "/home/caojia/miniconda3/envs/tts/lib/python3.10/site-packages/tn/chinese/normalizer.py", line 15, in from tn.processor import Processor File "/home/caojia/miniconda3/envs/tts/lib/python3.10/site-packages/tn/processor.py", line 23, in from pynini.lib import byte, utf8 File "/home/caojia/miniconda3/envs/tts/lib/python3.10/site-packages/pynini/lib/utf8.py", line 97, in "[240][159][135]" + TypeError: can only concatenate str (not "_pynini.Fst") to str

[jakeinflab]

I also experienced the same issue when integrating pynini on an arm64 system. I tried modifying the pynini code directly, but it still didn't work properly. I'm wondering if anyone has successfully resolved this problem.

我也在arm64系统上集成pynini时遇到了相同的问题。我尝试直接修改pynini代码，但它仍然无法正常工作。我想知道是否有人成功解决了这个问题。

[bingoforlesso]

我也有这个问题，苹果电脑，M4

[G1017]

你可以参考我的文章https://blog.csdn.net/qq_45080326/article/details/147513802?spm=1001.2014.3001.5501

[aspatic]

I also experienced the same issue when integrating pynini on an arm64 system. I tried modifying the pynini code directly, but it still didn't work properly. I'm wondering if anyone has successfully resolved this problem.

我也在arm64系统上集成pynini时遇到了相同的问题。我尝试直接修改pynini代码，但它仍然无法正常工作。我想知道是否有人成功解决了这个问题。

我先编译了openfst 然后用pip编译pynini最后安装WeTextProcessing 系统是 OpenEuler AArch64 + Ascend 910c

[aspatic]

但是最好的结果还是应该请官方要么开 cosyvoice-ttsfrd源码 要么给Arm64的预编译安装包 你可以看到他是只给了linux_x86_64的预编译wheel。 cd pretrained_models/CosyVoice-ttsfrd/

unzip resource.zip -d .
pip install ttsfrd_dependency-0.1-py3-none-any.whl
pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl

只要官方使能在aarch64上的编译安装cosyvoice-ttsfrd， 就可以完全绕过wetextprocessing 更别提 性能表现也更好 说话停顿更自然。

[zhd5120153951]

I also experienced the same issue when integrating pynini on an arm64 system. I tried modifying the pynini code directly, but it still didn't work properly. I'm wondering if anyone has successfully resolved this problem.

我也在arm64系统上集成pynini时遇到了相同的问题。我尝试直接修改pynini代码，但它仍然无法正常工作。我想知道是否有人成功解决了这个问题。

我先编译了openfst 然后用pip编译pynini最后安装WeTextProcessing 系统是 OpenEuler AArch64 + Ascend 910c

大佬你好，可以分享一下您的部署包镜像吗？昇腾部署CosyVoice太磨人了。