我们需要针对50系显卡的支持

我在5080显卡的电脑上尝试进行安装这个项目，但是始终会提示不支持cu128或者torch的版本，然后就会自动安装cu118的版本，即使我修改了install.py文件和st.py文件，替换了支持50系显卡的一些依赖也无法解决，下面是完整的安装和错误结果，安装完成后没有启动项目，直接关闭了服务：(videolingo) D:\video\VideoLingo>streamlit run st.py

You can now view your Streamlit app in your browser.

Local URL: http://localhost:8501
Network URL: http://192.168.3.218:8501

⚠️ Demucs导入失败，音频分离功能已禁用以支持RTX 5080兼容性: No module named 'demucs'
2025-07-29 12:08:42.191 Examining the path of torch.classes raised: Tried to instantiate class 'path.path', but it does not exist! Ensure that it is registered via torch::class
🎙️ Starting audio segmentation output/audio/raw.mp3 1800 60
E:\miniconda\envs\videolingo\lib\site-packages\pyannote\audio\core\io.py:43: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release.
torchaudio.set_audio_backend("soundfile")
E:\miniconda\envs\videolingo\lib\site-packages\torchaudio_internal\module_utils.py:71: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call.
return func(*args, **kwargs)
E:\miniconda\envs\videolingo\lib\site-packages\pyannote\audio\pipelines\speaker_verification.py:43: UserWarning: torchaudio._backend.get_audio_backend has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release.
backend = torchaudio.get_audio_backend()
E:\miniconda\envs\videolingo\lib\site-packages\torchaudio_internal\module_utils.py:71: UserWarning: torchaudio._backend.get_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call.
return func(*args, **kwargs)
E:\miniconda\envs\videolingo\lib\site-packages\speechbrain\utils\torch_audio_backend.py:57: UserWarning: torchaudio.backend.list_audio_backends has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release.
available_backends = torchaudio.list_audio_backends()
E:\miniconda\envs\videolingo\lib\site-packages\torch\backends_init.py:46: UserWarning: This API is going to be deprecated, please see https://pytorch.org/docs/main/notes/cuda.html#tensorfloat-32-tf32-on-ampere-and-later-devices (Triggered internally at C:\actions-runner_work\pytorch\pytorch\pytorch\aten\src\ATen\Context.cpp:81.)
self.setter(val)
E:\miniconda\envs\videolingo\lib\site-packages\pyannote\audio\pipelines\speaker_verification.py:45: UserWarning: Module 'speechbrain.pretrained' was deprecated, redirecting to 'speechbrain.inference'. Please update your script. This is a change from SpeechBrain 1.0. See: https://github.com/speechbrain/speechbrain/releases/tag/v1.0.0
from speechbrain.pretrained import (
E:\miniconda\envs\videolingo\lib\site-packages\pyannote\audio\pipelines\speaker_verification.py:53: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release.
torchaudio.set_audio_backend(backend)
E:\miniconda\envs\videolingo\lib\site-packages\pyannote\audio\tasks\segmentation\mixins.py:37: UserWarning: torchaudio.backend.common.AudioMetaData has been moved to torchaudio.AudioMetaData. Please update the import path.
from torchaudio.backend.common import AudioMetaData
🎤 Transcribing audio with local model...
🔍 Checking HuggingFace mirrors...
✓ HF-Mirror: 0.11s
✓ ModelScope: 0.03s
✗ Official: timeout
🚀 Selected mirror: https://modelscope.cn (0.03s)
🚀 Starting WhisperX using device: cuda ...
🎮 GPU memory: 15.92 GB, 📦 Batch size: 16, ⚙️ Compute type: float16
▶️ Starting WhisperX for segment 0.00s to 33.08s...
📥 Using WHISPER model from HuggingFace: large-v3 ...
You can ignore warning of Model was trained with torch 1.10.0+cu128...
Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: pip install huggingface_hub[hf_xet] or pip install hf_xet
model.bin: 100%|█████████████████████████████████████████████████████████████████▊| 3.09G/3.10G [03:04<00:00, 16.7MB/s]
Lightning automatically upgraded your loaded checkpoint from v1.5.4 to v2.5.2. To apply the upgrade to your files permanently, run python -m pytorch_lightning.utilities.upgrade_checkpoint E:\miniconda\envs\videolingo\lib\site-packages\whisperx\assets\pytorch_model.bin
Model was trained with pyannote.audio 0.0.1, yours is 3.1.1. Bad things might happen unless you revert pyannote.audio to 0.x.
Model was trained with torch 1.10.0+cu102, yours is 2.9.0. Bad things might happen unless you revert torch to 1.x.
Note: You will see Progress if working correctly ↓
Could not locate cudnn_ops_infer64_8.dll. Please make sure it is in your library path!

(videolingo) D:\video\VideoLingo>

Start by reviewing install.py and st.py, then reproduce the installation and startup flow on an RTX 5080 using the reported command. Trace the cu128 and torch dependency selection, Demucs import failure, and cudnn_ops_infer64_8.dll error; done means the project installs and starts successfully with the 50-series GPU without these failures.