运行示例代码报错 - Segmentation fault

[taozhixue]

先贴输出

2025-01-20 13:18:44,238 - modelscope - INFO - Loading ast index from /root/.cache/modelscope/ast_indexer
2025-01-20 13:18:44,273 - modelscope - INFO - Loading done! Current index file version is 1.15.0, with md5 2973eb2f0a4912b4a740c382bbe59769 and a total number of 980 components indexed
/root/miniconda3/envs/cosyvoice/lib/python3.10/site-packages/diffusers/models/lora.py:393: FutureWarning: `LoRACompatibleLinear` is deprecated and will be removed in version 1.0.0. Use of `LoRACompatibleLinear` is deprecated. Please switch to PEFT backend by installing PEFT: `pip install peft`.
  deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
2025-01-20 13:18:53,579 INFO input frame rate=25
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
2025-01-20 13:18:56.035531087 [E:onnxruntime:Default, provider_bridge_ort.cc:1480 TryGetProviderInfo_CUDA] /onnxruntime_src/onnxruntime/core/session/provider_bridge_ort.cc:1193 onnxruntime::Provider& onnxruntime::ProviderLibrary::Get() [ONNXRuntimeError] : 1 : FAIL : Failed to load library libonnxruntime_providers_cuda.so with error: libcublasLt.so.11: cannot open shared object file: No such file or directory

2025-01-20 13:18:56.035589198 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:747 CreateExecutionProviderInstance] Failed to create CUDAExecutionProvider. Please reference https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements to ensure all dependencies are met.
text.cc: festival_Text_init
open voice lang map failed
  0%|                                                                                                                                                                                                                  | 0/1 [00:00<?, ?it/s]2025-01-20 13:19:08,743 INFO synthesis text 在他讲述那个荒诞故事的过程中，他突然[laughter]停下来，因为他自己也被逗笑了[laughter]。
2025-01-20 13:19:32,031 INFO yield speech len 7.84, rtf 2.9704055919939156
Segmentation fault

和示例不一样的地方
因为我的cuda版本是12.2 所以onnx用的是1.17 onnxruntime-gpu最高只有1.16.3

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Tue_Jun_13_19:16:58_PDT_2023
Cuda compilation tools, release 12.2, V12.2.91
Build cuda_12.2.r12.2/compiler.32965470_0
(cosyvoice) [root@VM-54-123-centos CosyVoice]# pip list | grep onnx
onnx                     1.17.0
onnxruntime-gpu          1.16.3

运行时的GPU使用情况

+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.216.01             Driver Version: 535.216.01   CUDA Version: 12.2     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  Tesla T4                       On  | 00000000:00:09.0 Off |                  Off |
| N/A   71C    P0              69W /  70W |  10063MiB / 16384MiB |    100%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+
                                                                                         
+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
|    0   N/A  N/A     10735      C   python                                     3018MiB |
|    0   N/A  N/A     13935      C   ...rs/cuda_v12_avx/ollama_llama_server     3530MiB |
|    0   N/A  N/A     21094      C   ...rs/cuda_v12_avx/ollama_llama_server     3510MiB |
+---------------------------------------------------------------------------------------+

[aluminumbox]

看看是不是torchaudio跟机器不兼容