升级到main分支后发现，没有v0.94版本生成的好了

[mybolide]

升级到mast分支后发现，没有v0.94版本生成的好了
新版本添加Prompt 没效果，我打包了到zip里了，请大佬解惑
Music.zip

[mybolide]

似乎老版本的更接近真人

[jianchang512]

默认选中了 'refine text', 你可以取消试试

[mybolide]

for result in new_gen:
File "E:\chatTTS-ui_source\venv\Lib\site-packages\torch\utils_contextlib.py", line 35, in generator_context
response = gen.send(None)
^^^^^^^^^^^^^^
File "E:\chatTTS-ui_source\ChatTTS\model\gpt.py", line 570, in generate
for result in new_gen:
File "E:\chatTTS-ui_source\venv\Lib\site-packages\torch\utils_contextlib.py", line 35, in generator_context
response = gen.send(None)
^^^^^^^^^^^^^^
File "E:\chatTTS-ui_source\ChatTTS\model\gpt.py", line 438, in generate
outputs: BaseModelOutputWithPast = self.gpt(
^^^^^^^^^
File "E:\chatTTS-ui_source\venv\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\chatTTS-ui_source\venv\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\chatTTS-ui_source\venv\Lib\site-packages\transformers\models\llama\modeling_llama.py", line 978, in forward
layer_outputs = decoder_layer(
^^^^^^^^^^^^^^
File "E:\chatTTS-ui_source\venv\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\chatTTS-ui_source\venv\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\chatTTS-ui_source\venv\Lib\site-packages\transformers\models\llama\modeling_llama.py", line 732, in forward
hidden_states = self.mlp(hidden_states)
^^^^^^^^^^^^^^^^^^^^^^^
File "E:\chatTTS-ui_source\venv\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\chatTTS-ui_source\venv\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\chatTTS-ui_source\venv\Lib\site-packages\transformers\models\llama\modeling_llama.py", line 215, in forward
down_proj = self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 12.00 MiB. GPU 0 has a total capacity of 24.00 GiB of which 0 bytes is free. Of the allocated memory 34.59 GiB is allocated by PyTorch, and 3.69 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
我重新拉去代码后，发现提示CUDA超出内存了，显卡是24G的

[jianchang512]

显卡要看独立显存容量

另外或许有其他程序也在使用GPU，实际可用不足。

重新试试

[mybolide]

切换到v0.95 tag上之后 可以执行没有问题，好奇怪