Comments (9)
Chenyme
commented on July 20, 2024
非常感谢您的说明！！！
from chenyme-aavt.
Eisaichen
commented on July 20, 2024
感谢，这项目折腾了一天才跑起来，运用了你的commit修复
感觉这项目上限很高，但还很不成熟，遵循文档都跑不起来...
@Chenyme release V0.8.3是否应该撤回一下，因为这个commit下文件夹还是“models”但代码里路径已经改了，导致本地模型直接报错
我在英文系统下，一直因为代码里的中文运行不起来，提示"decode unicode charmap"什么的，通过设置环境变量PYTHONIOENCODING='utf-8'才解决
from chenyme-aavt.
Chenyme
commented on July 20, 2024
你好！感谢反馈！
个人水平时间有限，目前安装有点复杂，等考完后，会考虑其他办法简化步骤。
commit下文件夹还是“models”但代码里路径已经改了 我看了一下commit，路径应该是和0.8.3一样的。
在英文系统下，一直因为代码里的中文运行不起来 代码中有许多是中文说明，可能这是出错的原因。
from chenyme-aavt.
Eisaichen
commented on July 20, 2024
@Chenyme 麻烦你检查0.8.3a25de34里文件夹是命名为Models，再看看这个Commit下的project/video.py第18行
from chenyme-aavt.
Chenyme
commented on July 20, 2024
了解啦。由于我之前操作有误，导致所有的Tag标签中，每个标签对应的项目代码都是上一个版本的内容，一直未做调整。实在不好意思啊(┬┬﹏┬┬)
所以Git项目，请以main分支为准。
直接下载，还请以releases各版本中的压缩包为准。
感谢
from chenyme-aavt.
Eisaichen
commented on July 20, 2024
@Chenyme 另外请问下要如何本地加载原版的Whisper模型？
选whisper后会报错 (同环境下fast-whisper可正常使用)
Logs
chenyme-aavt | 2024-06-13 01:50:55.905 Uncaught app exception
chenyme-aavt | Traceback (most recent call last):
chenyme-aavt | File "C:\Users\ContainerAdministrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 600, in _run_script
chenyme-aavt | exec(code, module.__dict__)
chenyme-aavt | File "C:\app\Chenyme-AAVT.py", line 41, in <module>
chenyme-aavt | video()
chenyme-aavt | File "C:\app\project\video.py", line 425, in video
chenyme-aavt | result = faster_whisper_result(output_file, device, model, whisper_prompt_setting, temperature_setting, vad_setting, lang_setting, beam_size_setting, min_vad_setting)
chenyme-aavt | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
chenyme-aavt | File "C:\app\project\utils\utils2.py", line 107, in faster_whisper_result
chenyme-aavt | model = WhisperModel(model_name, device)
chenyme-aavt | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
chenyme-aavt | File "C:\Users\ContainerAdministrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\faster_whisper\transcribe.py", line 144, in __init__
chenyme-aavt | self.model = ctranslate2.models.Whisper(
chenyme-aavt | ^^^^^^^^^^^^^^^^^^^^^^^^^^^
chenyme-aavt | RuntimeError: Unsupported model binary version. This executable supports models with binary version v6 or below, but the model has binary version v67324752. This usually means that the model was generated by a later version of CTranslate2. (Forward compatibility is not guaranteed.)
模型是直接从hf上clone的
File list
C:\CONTAINERS\CHENYME-AAVT\MODEL\WHISPER-LARGE-V3
.gitattributes
added_tokens.json
config.json
flax_model.msgpack
generation_config.json
merges.txt
model.fp32-00001-of-00002.safetensors
model.fp32-00002-of-00002.safetensors
model.safetensors
model.safetensors.index.fp32.json
normalizer.json
preprocessor_config.json
pytorch_model.bin
pytorch_model.bin.index.fp32.json
pytorch_model.fp32-00001-of-00002.bin
pytorch_model.fp32-00002-of-00002.bin
README.md
special_tokens_map.json
tokenizer.json
tokenizer_config.json
vocab.json
from chenyme-aavt.
Chenyme
commented on July 20, 2024
启用本地模型只支持fast-whisper的模型哈
因为fast-whisper使用的模型是基于CTranslate2 转换的，因此原openai的不支持。
该模型从huggingface/Systran下载ヾ(≧▽≦*)o
具体使用可参考AAVT文档中的本地模型加载使用说明
from chenyme-aavt.
Eisaichen
commented on July 20, 2024
@Chenyme 主贴的这个fix能整合一下嘛？这个问题我这里100%会出现，每次新版本我都得改代码
这个issue在faster-whisper提出1年多了都没修，大概是指望不上了，只能先workaround
from chenyme-aavt.
Chenyme
commented on July 20, 2024
@Chenyme 主贴的这个fix能整合一下嘛？这个问题我这里100%会出现，每次新版本我都得改代码
这个issue在faster-whisper提出1年多了都没修，大概是指望不上了，只能先workaround
好滴！最近期末考，可能晚点会合并😃
from chenyme-aavt.
Related Issues (20)
- 爆出openai_key不存在 HOT 1
- Kimi Translation Function Reach the Limit of API Request HOT 2
- 无法使用chatgpt中转站 HOT 1
- 第一次使用出现如下错误 HOT 1
- torch+CUDA安装后CUDA加速不可用 HOT 7
- 网页中点击运行程序报错，命令框闪退 HOT 7
- streamlit server can not be connected HOT 1
- OpenMP HOT 1
- 中转站无法正常调用 HOT 5
- 点了install.bat完了不会使用，如何卸载？ HOT 4
- 主要是我小白基础太差，哈哈！还得进一步学习下
- 关于个别bug的探讨 HOT 2
- 希望有docker部署版本 HOT 3
- 音频太大会超出限制（200M+） HOT 1
- 是否可以提供双语字幕功能 HOT 2
- 希望能支持音频直接提取字幕的功能 HOT 3
- 希望在翻译时允许使用自定义的提示词 HOT 2
- 希望支持使用Google Gemini /Gemini pro进行翻译 HOT 2
- Feature Docker部署Debian 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 chenyme-aavt.