Comments (16)
步骤3这个错误说明视频没下下来,看下你的txt
from vits-fast-fine-tuning.
speaker_link2.txt
是格式错了么
from vits-fast-fine-tuning.
from vits-fast-fine-tuning.
收到,我会试试的
from vits-fast-fine-tuning.
我用你的文件试了一下,没有任何问题,标注也正常生成了
long_character_anno.txt
from vits-fast-fine-tuning.
经测试可能是因为whisper没能正常运行导致的,刚刚把模型型号从large换成了medium,你现在再试试看
from vits-fast-fine-tuning.
又试了一遍,步骤三还是步骤三不一样
transcribing ./denoised_audio/vangogh_29936.wav...
transcribing ./denoised_audio/vangogh_583238.wav...
2023-02-26 16:42:38.096489: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-02-26 16:42:39.331181: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/lib/python3.8/dist-packages/cv2/../../lib64:/usr/lib64-nvidia
2023-02-26 16:42:39.331316: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/lib/python3.8/dist-packages/cv2/../../lib64:/usr/lib64-nvidia
2023-02-26 16:42:39.331336: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
from vits-fast-fine-tuning.
这个打印的信息是正确的,看一下有没有生成long_character_anno.txt这个文件,有的话就没问题了
from vits-fast-fine-tuning.
好,明晚试试,感谢
from vits-fast-fine-tuning.
好,明晚试试,感谢
用你给的链接把梵高模型炼好了,效果还不错,在这里下载:
https://drive.google.com/drive/folders/1OICqnvcge55Hd7Ja8eIE0PzQZr4MHBRx?usp=sharing
感谢你为debug做出的贡献,爱你🤗
from vits-fast-fine-tuning.
谢谢谢谢OTZ
from vits-fast-fine-tuning.
我也是同样的错误 用的视频链接 没有看到下面生成long_character_anno.txt那个文件,还是说我没找到吗?导入视频也是一样的结果
这是我的链接文件speaker_link2.txt
Running this codeblock will perform automatic vocal seperation & annotation. Since this step uses Whisper & Demucs, it may take a while to complete.
[MoviePy] Writing audio in ./raw_audio/madoka_652407.wav
100%|██████████| 5890/5890 [00:03<00:00, 1750.28it/s]
[MoviePy] Done.
speaker_link2.txt
[MoviePy] Writing audio in ./raw_audio/madoka_645071.wav
100%|██████████| 5890/5890 [00:02<00:00, 2184.38it/s]
[MoviePy] Done.
[MoviePy] Writing audio in ./raw_audio/madoka_271353.wav
100%|██████████| 5890/5890 [00:02<00:00, 2476.39it/s]
[MoviePy] Done.
Important: the default model was recently changed to htdemucs
the latest Hybrid Transformer Demucs model. In some cases, this model can actually perform worse than previous models. To get back the old default model use -n mdx_extra_q
.
Selected model is a bag of 1 models. You will see that many progress bars per track.
Separated tracks will be stored in /content/VITS-fast-fine-tuning/VITS-fast-fine-tuning/VITS-fast-fine-tuning/separated/htdemucs
Separating track raw_audio/madoka_645071.wav
100%|██████████████████████████████████████████████| 269.09999999999997/269.09999999999997 [00:14<00:00, 18.44seconds/s]
Important: the default model was recently changed to htdemucs
the latest Hybrid Transformer Demucs model. In some cases, this model can actually perform worse than previous models. To get back the old default model use -n mdx_extra_q
.
Selected model is a bag of 1 models. You will see that many progress bars per track.
Separated tracks will be stored in /content/VITS-fast-fine-tuning/VITS-fast-fine-tuning/VITS-fast-fine-tuning/separated/htdemucs
Separating track raw_audio/madoka_652407.wav
100%|██████████████████████████████████████████████| 269.09999999999997/269.09999999999997 [00:13<00:00, 19.90seconds/s]
Important: the default model was recently changed to htdemucs
the latest Hybrid Transformer Demucs model. In some cases, this model can actually perform worse than previous models. To get back the old default model use -n mdx_extra_q
.
Selected model is a bag of 1 models. You will see that many progress bars per track.
Separated tracks will be stored in /content/VITS-fast-fine-tuning/VITS-fast-fine-tuning/VITS-fast-fine-tuning/separated/htdemucs
Separating track raw_audio/madoka_271353.wav
100%|██████████████████████████████████████████████| 269.09999999999997/269.09999999999997 [00:13<00:00, 19.92seconds/s]
2023-03-04 05:08:21.936022: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-03-04 05:08:23.588622: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/lib/python3.8/dist-packages/cv2/../../lib64:/usr/local/lib/python3.8/dist-packages/cv2/../../lib64:/usr/lib64-nvidia
2023-03-04 05:08:23.588800: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/lib/python3.8/dist-packages/cv2/../../lib64:/usr/local/lib/python3.8/dist-packages/cv2/../../lib64:/usr/lib64-nvidia
2023-03-04 05:08:23.588833: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
transcribing ./denoised_audio/madoka_645071.wav...
transcribing ./denoised_audio/madoka_652407.wav...
transcribing ./denoised_audio/madoka_271353.wav...
2023-03-04 05:12:11.501043: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-03-04 05:12:13.146523: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/lib/python3.8/dist-packages/cv2/../../lib64:/usr/lib64-nvidia
2023-03-04 05:12:13.146706: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/lib/python3.8/dist-packages/cv2/../../lib64:/usr/lib64-nvidia
2023-03-04 05:12:13.146741: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
Warning: no short audios found, this IS expected if you have only uploaded long audios, videos or video links.
this IS NOT expected if you have uploaded a zip file of short audios. Please check your file structure or make sure your audio language is supported.
from vits-fast-fine-tuning.
打印的信息应该是对的,没找到就刷新一下,我会用你链接的测试一遍
from vits-fast-fine-tuning.
打印的信息应该是对的,没找到就刷新一下,我会用你链接的测试一遍
刷新重试了一下,现在多了这个
Traceback (most recent call last):
File "long_audio_transcribe.py", line 45, in
code = file.rstrip(".wav").split("_")[1]
IndexError: list index out of range
from vits-fast-fine-tuning.
是没有问题的,如果还是不行建议检查一下GPU是否开启,或者重启会话。
from vits-fast-fine-tuning.
好的,谢谢大佬~
from vits-fast-fine-tuning.
Related Issues (20)
- Step 1 多个地方报错 HOT 3
- 已解决:训练之后如何保存模型问题 HOT 3
- 在其他云上运行脚本的step3.5出现的问题
- step3.5出错 HOT 2
- 纯中文模型如何转换成onnx格式 HOT 1
- 【本地运行错误】AssertionError [12700] Failed to execute script 'inference' due to unhandled exception! HOT 2
- vits推理的时候怎么得到每个音素的时长?
- 明明上传了文件,结果google colab的步骤3.5出现了问题 HOT 7
- 本地合成时跳出此错误:"不是内部或外部命令,也不是可运行的程序或批处理文件。"
- [[已解決]]求助~長短 audio 在開始訓練前處理載入的數據時有問題 HOT 1
- 后续会出Mac版本的inference吗?
- 请问如何获得.index索引,谢谢
- 求助 RuntimeError: unmatched '}' in format string
- 想了解下如何弄成一个后端API请求接口 HOT 1
- 求助, 关于文字数量影响生成音频的速度问题 HOT 2
- 大佬,处理长音频时一直出现list index out of range问题,咋办 HOT 2
- 训练纯日文200轮长音频,但是生成出来的语音末尾戛然而止,不自然 HOT 2
- 請問有關cuda memory的問題
- 多条文本并行推理,生成的语音如何确定填充起始点
- STEP 4報錯「找不到音檔」:No such file or directory: '\ufeff./custom_character_voice/Reiya/processed_0.wav' HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from vits-fast-fine-tuning.