lujun1996
发表于 2025-5-24 00:40:44
小红书的更新也是这么快的吗？刚刚看到第一稿，现在就是第二稿了，真是快啊
dnbc
发表于 2025-6-4 12:22:01
试试效果怎么样
ph.li
发表于 2025-9-8 19:59:41
能帮忙看下吗？我解压之后运行，RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.； 在这个日志之前，启动的时候提示这些：C:\work\soft\FireRedTTS-V2\fireredtts\modules\codec\speaker.py:1040: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. model.load_state_dict(torch.load(ckpt_path), strict=True) C:\work\soft\FireRedTTS-V2\python\Lib\site-packages\torch\cuda\__init__.py:230: UserWarning: NVIDIA GeForce RTX 5080 Laptop GPU with CUDA capability sm_120 is not compatible with the current PyTorch installation. The current PyTorch install supports CUDA capabilities sm_50 sm_60 sm_61 sm_70 sm_75 sm_80 sm_86 sm_90. If you want to use the NVIDIA GeForce RTX 5080 Laptop GPU GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/ warnings.warn( C:\work\soft\FireRedTTS-V2\fireredtts\fireredtts.py:51: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. sd = torch.load(self.gpt_path, map_location=device)["model"] C:\work\soft\FireRedTTS-V2\python\Lib\site-packages\torch\nn\utils\weight_norm.py:134: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`. WeightNorm.apply(module, name, dim) C:\work\soft\FireRedTTS-V2\fireredtts\fireredtts.py:62: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. sd = torch.load(self.token2wav_path, map_location="cpu") Removing weight norm... Running on local URL:http://127.0.0.1:7860To create a public link, set `share=True` in `launch()`.
ph.li
发表于 2025-9-8 20:01:37
ph.li 发表于 2025-9-8 19:59
能帮忙看下吗？我解压之后运行，RuntimeError: CUDA error: no kernel image is available for execution o ...
我本地的是：
C:\Users\15801>nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2025 NVIDIA Corporation
Built on Wed_Jan_15_19:38:46_Pacific_Standard_Time_2025
Cuda compilation tools, release 12.8, V12.8.61
Build cuda_12.8.r12.8/compiler.35404655_0
无言以对
发表于 2025-9-8 21:50:45
ph.li 发表于 2025-9-8 20:01
我本地的是：
C:%users\15801>nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
论坛里标题或者帖子里除非有特殊说明，否则是不支持50系显卡
bin313784868
发表于 2025-9-8 23:28:37
太虚需要这个了
ph.li
发表于 2025-9-9 16:24:15
无言以对 发表于 2025-9-8 21:50
论坛里标题或者帖子里除非有特殊说明，否则是不支持50系显卡
嗯嗯，我换了台老的设备，就好了；
再请教个问题，这个模型官方是支持副语言的， 比如笑声啥的；但是这里的这个版本，我没有试出来？是这款不支持吗？还是说哪里需要配置的
无言以对
发表于 2025-9-9 16:37:53
ph.li 发表于 2025-9-9 16:24
嗯嗯，我换了台老的设备，就好了；
再请教个问题，这个模型官方是支持副语言的， 比如笑声啥的；但是这里 ...
一般笑声需要控制符号激活，你看看官方文档有没有类似激活说明
我没仔细研究过
zhbkq
发表于 2025-9-12 12:20:47
感谢楼主分享啦