GPU版找不到文件model_blade.torchscript

[Jotree2012]

Notice: In order to resolve issues more efficiently, please raise issue following the template.
（注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节）

❓ Questions and Help

Before asking:

1. search the issues.
2. search the docs.

What is your question?

运行WSL-Ubuntu-Docker GPU版 提示这个模型里没有文件 model_blade.torchscript

按照官网https://github.com/modelscope/FunASR/blob/main/runtime/docs/SDK_advanced_guide_offline_gpu_zh.md
到最后一步
nohup bash run_server.sh
--download-model-dir /workspace/models
--vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx
--model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch
--punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx
--lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst
--itn-dir thuduj12/fst_itn_zh
--hotword /workspace/models/hotwords.txt > log.txt 2>&1 &

执行后，查看log.txt
tail -f log.txt
If you want to use ffmpeg backend to load audio, please install it by:
sudo apt install ffmpeg # ubuntu
# brew install ffmpeg # mac
transformer is not installed, please install it if you want to use related modules
model is not exist, begin to export /workspace/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model_blade.torchscript
funasr version: 1.1.8.
Check update of funasr, and it would cost few times. You may disable it by set disable_update=True in AutoModel
New version is available: 1.1.14.
Please use the command "pip install -U funasr" to upgrade.
Downloading: 100%|██████████| 6.00k/6.00k [00:00<00:00, 18.3kB/s]
Downloading: 100%|██████████| 10.9k/10.9k [00:00<00:00, 38.9kB/s]
Downloading: 100%|██████████| 408k/408k [00:00<00:00, 897kB/s]
Downloading: 100%|██████████| 2.83k/2.83k [00:00<00:00, 9.47kB/s]
Downloading: 100%|██████████| 693/693 [00:00<00:00, 2.22kB/s]
Downloading: 100%|██████████| 859M/859M [01:21<00:00, 11.0MB/s]
Downloading: 100%|██████████| 19.2k/19.2k [00:00<00:00, 55.9kB/s]
Downloading: 100%|██████████| 7.90M/7.90M [00:01<00:00, 6.52MB/s]
Downloading: 100%|██████████| 48.7k/48.7k [00:00<00:00, 130kB/s]
Downloading: 100%|██████████| 91.5k/91.5k [00:00<00:00, 196kB/s]
Traceback (most recent call last):
File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/workspace/FunASR/funasr/download/runtime_sdk_download_tool.py", line 58, in
main()
File "/workspace/FunASR/funasr/download/runtime_sdk_download_tool.py", line 51, in main
export_model.export(
File "/workspace/FunASR/funasr/auto/auto_model.py", line 662, in export
export_dir = export_utils.export(model=model, data_in=data_list, **kwargs)
File "/workspace/FunASR/funasr/utils/export_utils.py", line 31, in export
assert (
AssertionError: Currently bladedisc optimization for FunASR only supports GPU
I20241108 06:19:07.329227 161 funasr-wss-server.cpp:308] Failed to download model from modelscope. If you set local asr model path, you can ignore the errors.
E20241108 06:19:07.330305 161 funasr-wss-server.cpp:312] /workspace/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model_blade.torchscript do not exists.

What have you tried?

有damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch模型，想要手动重新下载，发现ModelScope对应模型文件夹下并没有文件model_blade.torchscript

What's your environment?

WSL-Ubuntu-Docker
WSL2.0
Ubuntu22.04
Docker version 24.0.7, build 24.0.7-0ubuntu2~22.04.1

[Jotree2012]

删除/workspace/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch后，
重新运行命令
日志如下：报错不能下载模型
root@88336fc22380:/workspace/FunASR/runtime# tail -f log.txt
Key Conformer already exists in model_classes, re-register
Key Linear already exists in adaptor_classes, re-register
Key TransformerDecoder already exists in decoder_classes, re-register
Key LightweightConvolutionTransformerDecoder already exists in decoder_classes, re-register
Key LightweightConvolution2DTransformerDecoder already exists in decoder_classes, re-register
Key DynamicConvolutionTransformerDecoder already exists in decoder_classes, re-register
Key DynamicConvolution2DTransformerDecoder already exists in decoder_classes, re-register
transformer is not installed, please install it if you want to use related modules
I20241108 06:46:43.440191 1214 funasr-wss-server.cpp:235] Set vad-dir : /workspace/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx
I20241108 06:46:43.440222 1214 funasr-wss-server.cpp:289] Download model: damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch from modelscope:
Traceback (most recent call last):
File "/usr/lib/python3.8/runpy.py", line 185, in _run_module_as_main
mod_name, mod_spec, code = _get_module_details(mod_name, _Error)
File "/usr/lib/python3.8/runpy.py", line 111, in _get_module_details
import(pkg_name)
File "/usr/local/lib/python3.8/dist-packages/funasr/init.py", line 37, in
import_submodules(name)
File "/usr/local/lib/python3.8/dist-packages/funasr/init.py", line 33, in import_submodules
results.update(import_submodules(name))
File "/usr/local/lib/python3.8/dist-packages/funasr/init.py", line 25, in import_submodules
for loader, name, is_pkg in pkgutil.walk_packages(package.path, package.name + "."):
File "/usr/lib/python3.8/pkgutil.py", line 92, in walk_packages
import(info.name)
File "/usr/local/lib/python3.8/dist-packages/funasr/models/eres2net/init.py", line 1, in
from .eres2net import ERes2Net
File "/usr/local/lib/python3.8/dist-packages/funasr/models/eres2net/eres2net.py", line 14, in
import torch
File "/usr/local/lib/python3.8/dist-packages/torch/init.py", line 233, in
for name in dir(_C):
NameError: name '_C' is not defined
I20241108 06:46:44.063077 1214 funasr-wss-server.cpp:308] Failed to download model from modelscope. If you set local asr model path, you can ignore the errors.
E20241108 06:46:44.063591 1214 funasr-wss-server.cpp:312] /workspace/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model_blade.torchscript do not exists.

[Jotree2012]

是版本太高了？
root@6e761e19fa76:/workspace/FunASR/runtime# nvidia-smi
Fri Nov 8 07:54:45 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 565.51.01 Driver Version: 565.90 CUDA Version: 12.7 |
|-----------------------------------------+------------------------+----------------------+
| 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 NVIDIA GeForce RTX 4090 D On | 00000000:01:00.0 On | Off |
| 0% 49C P8 12W / 425W | 1289MiB / 24564MiB | 6% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 33 G /Xwayland N/A |