jianchang512/pyvideotrans issues and pull requests

#736 - 不识别本地 faster-whisper-large-v3-turbo 文件

Issue - State: closed - Opened by 1-1-2 2 days ago - 2 comments

#734 - Request: Is possible add all model from GEMINI 2.0

Issue - State: open - Opened by johnfelipe 3 days ago - 3 comments

#733 - there is bug in pyvideotrans 3.53 when using f5tts to store timestamp as separate audio file. Error in dubbing:[Errno 2] No such file or directory: 'E:/pyvideotrans new/win-videotrans-v3.53-tiny/tmp/dubbing_cache/773930-776130-1739864337.921336

Issue - State: open - Opened by abhijeet12s 3 days ago - 6 comments

#732 - 可以对接下火山引擎的声音复刻大模型吗

Issue - State: open - Opened by openoo 6 days ago

#731 - please please please 😓😓 add this Feature : Currently, F5TTS generates a single continuous audio file when processing subtitles. I need an option where the software automatically saves individual MP3 files corresponding to each timestamp i

Issue - State: open - Opened by abhijeet12s 8 days ago

#730 - 请请请 😓😓 添加这个功能请求：in pyvideotrans 3.53 目前，F5TTS 在处理字幕时会生成一个连续的音频文件。我需要一个选项，让软件可以自动将音频按 SRT 文件中的时间戳分别保存为单独的 MP3 文件。

Issue - State: open - Opened by abhijeet12s 8 days ago

#729 - the alignment of video footage and audio footage is wrong and its alignment not matching in pyvideotrans 3.50 , 3.52

Issue - State: open - Opened by abhijeet12s 9 days ago

#728 - 📍📌adding feature of creating image narration using Gemini , i have readymade code for this just implement it,first its generates details of images then paste those all into chatgpt or gemini yourself manually to generate narration

Issue - State: open - Opened by abhijeet12s 9 days ago

#727 - openai翻译模式字幕中有换行符号，只翻译换行符前面的文字

Issue - State: open - Opened by lin16303 10 days ago

#725 - in pyvideotrans 3.49 why is GLM-4-flash(免费) , Qwen2.5-7b(免费) translation not working. when i press start it does not start.

Issue - State: open - Opened by abhijeet12s 15 days ago - 1 comment

#724 - In version 3.18, I could dub 30 subtitles at once, and dubbing a 45-minute video took about 1 hour. However, in version 3.49, both the software and dubbing process have slowed down, now taking 6-7 hours for the same video. The slowdown is not just....

Issue - State: open - Opened by abhijeet12s 16 days ago - 3 comments

#723 - After selecting the Paraformer-ZH model for speech recognition and setting the CJK line length to 40, the output remains the same as with the 20-character setting, without reflecting the expected 40-character line length. which is troublesome

Issue - State: open - Opened by abhijeet12s 16 days ago - 1 comment

#722 - kokoro-uiapi-v0.1.7z (2.1G) which is for windows is not downloading, its showing that The download quota for this file has been exceeded. as you can see in the screenshot that i have uploaded

Issue - State: closed - Opened by abhijeet12s 17 days ago

#721 - weird behaviour in windows 11 pro with latest version

Issue - State: open - Opened by johnfelipe 17 days ago - 1 comment

#720 - how can import/export settings from v3.46 to v3.48

Issue - State: closed - Opened by johnfelipe 17 days ago - 2 comments

#719 - language

Issue - State: open - Opened by Manoj132466 19 days ago

#718 - 3.46 deepseek v3默认翻译提示词，返回较多<output><input>指令符

Issue - State: open - Opened by lin16303 21 days ago - 1 comment

#717 - youtube download failing

Issue - State: closed - Opened by johnfelipe 22 days ago - 4 comments

#716 - 本地ollama模型字幕翻译翻译为空白

Issue - State: open - Opened by wdd500 25 days ago

#714 - 目标语言选择泰国语的时候火山语言合成选不了配音角色

Issue - State: open - Opened by gujiangfeng 28 days ago

#713 - Edge-TTS经常出错，靠不住啊！MultiTTS对接自定义TTS-API有人会吗？

Issue - State: open - Opened by fzlsj about 1 month ago

#710 - 视频字幕画面对齐功能里两个小问题

Issue - State: open - Opened by Sally-fyk about 1 month ago

#709 - 能否添加kokoro tts api 功能？

Issue - State: open - Opened by okayshare about 1 month ago - 2 comments

#708 - alway got FileNotFoundError error.

Issue - State: closed - Opened by stonegate8 about 1 month ago

#707 - the pyvideotrans 3.46 gemini translation feature is translating srt wierdly

Issue - State: open - Opened by abhijeet12s about 1 month ago

#706 - 预处理阶段出错:Command

Issue - State: open - Opened by getmonyinfo about 1 month ago - 3 comments

#703 - 是否有视频加速功能？

Issue - State: open - Opened by midjzero about 1 month ago - 1 comment

#702 - 优化了多角色配音的角色选择

Pull Request - State: closed - Opened by ok3721 about 1 month ago

#701 - azure open ai very slow translation

Issue - State: open - Opened by johnfelipe about 1 month ago

#699 - Gemini Pro 1.5 got error Too many requests

Issue - State: open - Opened by dokimkhanh about 2 months ago

#697 - 3.39-3.42 IndexError: list index out of range, 用3.06正常

Issue - State: open - Opened by lin16303 about 2 months ago - 1 comment

#696 - 您好，作者

Issue - State: open - Opened by Camelhouse1 about 2 months ago - 1 comment

#694 - 能不能增加一个功能，让生成的字幕能与音频在同一个文件夹

Issue - State: open - Opened by dcyy-l about 2 months ago

#692 - got an unexpected keyword argument 'threshold'"

Issue - State: closed - Opened by blissvisitor about 2 months ago - 6 comments

#691 - 打不开

Issue - State: open - Opened by hixcao about 2 months ago

#690 - CUDA not works after update nvidia studio Versión: 566.36 - Publicados: Tue Dec 10, 2024

Issue - State: closed - Opened by johnfelipe about 2 months ago - 3 comments

#689 - windows-videotrans-v3.41 issue / [0%] Error: The file name or directory cannot be created. If you need to use Chinese characters, please set global encoding to UTF8. The problematic file name: "Agent Builder with BiqQuery (SQL Agent on Google Cloud) - Tutorial AcNSxfqZ2UJ6S.mp4"

Issue - State: open - Opened by johnfelipe about 2 months ago

#688 - elevenlabs new version of model

Issue - State: open - Opened by johnfelipe about 2 months ago - 1 comment

#687 - OpenAl在线api语音识别使用第三方时报错"'TranscriptionSegment' object is not subscriptable"

Issue - State: open - Opened by xwxYa 2 months ago - 4 comments

#686 - 考虑过支持AMD GPU加速吗

Issue - State: open - Opened by ruby-ya 2 months ago

#685 - Can you add image narration feature in the pyvideotrans. I have provided refference code in the chat

Issue - State: open - Opened by abhijeet12s 2 months ago

#684 - 一次选择30个以上视频顺序翻译后【队列模式，一次只处理一个视频】，会导致每个视频的处理变慢大概10倍

Issue - State: closed - Opened by WangShuXian6 2 months ago

#683 - v339, 开启保留原始背景音选项后，开场的无人生有bgm的视频会被切除，但bgm依然保留，导致整个画面比人声早秒。

Issue - State: open - Opened by WangShuXian6 2 months ago

#682 - v339 有概率后半部分视频只有音频，视屏画面永远静止在某一帧。326版本没有这个问题。

Issue - State: open - Opened by WangShuXian6 2 months ago

#681 - Avoid converting all values to lowercase upon each configuration load.

Pull Request - State: closed - Opened by zhyi828 2 months ago

#680 - jp av 转录翻译效果怎么样啊

Issue - State: closed - Opened by qhgy 2 months ago

#679 - TTS合成语音，最终视频音频码率下降

Issue - State: open - Opened by gsessylu 2 months ago

#678 - VideoTrans - ERROR - 字幕翻译失败,No content

Issue - State: open - Opened by sdwcn 2 months ago - 5 comments

#677 - First Time run Error

Issue - State: open - Opened by MimojiAzua 2 months ago

#676 - First time run error

Issue - State: closed - Opened by MimojiAzua 2 months ago - 1 comment

#675 - 3.38 f5clone配音报错

Issue - State: open - Opened by lin16303 2 months ago - 2 comments

#673 - what happend with this file in updating?

Issue - State: open - Opened by johnfelipe 2 months ago - 3 comments

#672 - v3.37。Github源。设置本地ollama接口出现报错：VideoTrans - ERROR - 字幕翻译失败,Client.init() got an unexpected keyword argument 'proxies'。在更改httpx库的版本后，报出新问题：[LocalLLM]:连接服务失败无法连接当前AP:http:/127.0.0.1:11434 connection error

Issue - State: open - Opened by BY9267 2 months ago - 12 comments

#670 - 3.36本地大模型翻译prompt格式与旧版不同，翻译速度大幅下降

Issue - State: open - Opened by lin16303 2 months ago - 3 comments

#669 - 批量翻译出错

Issue - State: closed - Opened by gatsby-coder 2 months ago

#668 - 336本地大模型翻译报错Exception: 字幕翻译失败,No content

Issue - State: closed - Opened by lin16303 2 months ago - 1 comment

#667 - 3.36勾选视频慢速尝试硬件会导致背景分离时仅cpu工作

Issue - State: open - Opened by lin16303 2 months ago - 2 comments

#666 - 3.34翻译srt字幕的问题

Issue - State: open - Opened by doublex640 2 months ago

#665 - 有关 README.md 的修复

Pull Request - State: closed - Opened by KKiiya 2 months ago

#664 - 修正了 README.md 中的错误命令

Pull Request - State: closed - Opened by KKiiya 2 months ago

#663 - 3.33版本点击开始后一直卡在不动

Issue - State: open - Opened by secondly 2 months ago

#662 - 3.33调用外部配音阶段，后台ffmpeg的cpu占用率始终超高，这个进程是否有效？

Issue - State: open - Opened by lin16303 2 months ago - 1 comment

#661 - 背景分离306，gpu 100%，cpu占用率较低，333只有cpu拉满，gpu占用率为0

Issue - State: open - Opened by lin16303 3 months ago - 1 comment

#660 - 嵌入双语字幕后没有分行显示

Issue - State: closed - Opened by ceeeeeeeeeeeeeeeeb 3 months ago - 1 comment

#659 - 3.33 returned non-zero exit status 4294967294.

Issue - State: open - Opened by lin16303 3 months ago - 4 comments

#658 - 执行任务报错

Issue - State: open - Opened by PzzzZang 3 months ago

#657 - 能为gemini服务增加负载均衡轮询吗？以便使用增加vad切割为小片段再挨个发送请求识别，以避免时间戳不准确问题

Issue - State: open - Opened by elfcute 3 months ago

#656 - 使用gemini识别转录报错’VadOptions. init_0 got an unexpected keyword argument 'threshold'

Issue - State: open - Opened by elfcute 3 months ago - 2 comments

#655 - 3.30 with some CUDA problem? Taking too long

Issue - State: open - Opened by jivagotupa 3 months ago - 2 comments

#654 - 升到3.30以后，生成的视频花掉。3.28同样参数没问题。

Issue - State: open - Opened by ilengyue1 3 months ago

#653 - 打开重新断句，英文之间连在一起没有空格

Issue - State: open - Opened by gatsby-coder 3 months ago

#652 - 升级最新版本后设置多角色音效不成功

Issue - State: open - Opened by Eddyzhu520 3 months ago

#651 - Processing Stuck at Subtitle Alignment Step

Issue - State: closed - Opened by naolip 3 months ago - 4 comments

#650 - 运行api.exe出现JSONDecodeError

Issue - State: open - Opened by gsessylu 3 months ago

#649 - Add Preset Option - Pause between stages

Issue - State: open - Opened by jivagotupa 3 months ago - 4 comments

#648 - 如何使用FunASR的Emotion2Vec+ Large模型转录音频 , you can see the code that works but transcribes audio in text i want it in srt

Issue - State: open - Opened by abhijeet12s 3 months ago - 1 comment

#647 - iic/SenseVoiceSmall is not registered

Issue - State: open - Opened by dcyy-l 3 months ago - 4 comments

#646 - error with 3.26 - I cant see my custom profile in elevenlabs

Issue - State: closed - Opened by johnfelipe 3 months ago - 2 comments

#645 - error with 3.26 - TEST GET ROLES - elevenlabs with subscription - pydantic_core_pydantic_core.cp310-win_amd64.pyd

Issue - State: closed - Opened by johnfelipe 3 months ago - 3 comments

#644 - remove_noise ERROR

Issue - State: closed - Opened by moseleman 3 months ago - 1 comment

#643 - There are multiple characters in the video, such as ABCD. How to translate the video? Settings?

Issue - State: open - Opened by kernelpod 3 months ago - 2 comments

#642 - elevenlabs dubbed english to spanish v3.2 / gemini 1.5 pro

Issue - State: closed - Opened by johnfelipe 3 months ago - 6 comments

#641 - f5-tts error

Issue - State: open - Opened by pratikboss19 3 months ago - 3 comments

#640 - 如何区分笑声？

Issue - State: open - Opened by MonolithFoundation 3 months ago

#639 - v3.20 missing something / No package metadata was found for The ‘tqdm>=4.27 distribution was not found and is requi

Issue - State: closed - Opened by johnfelipe 3 months ago - 1 comment

#638 - WhisperX 好用免费语音识别模型，同时还有区别发言，就是传说说话人分离

Issue - State: open - Opened by joe12801 3 months ago

#637 - Feat: Gemini语音识别时增加vad切割为小片段再挨个发送请求识别，以避免时间戳不准确问题，翻译设置Gemini pro中启用(免费Gemini账号勿启用，会导致大量429错误)

Issue - State: closed - Opened by johnfelipe 3 months ago - 2 comments

#636 - f5-tts is making weird dubbing , you can see in provided audio and srt its horrible, but its working fine in WebView, why cant it create audio properly pyvideotrans ?

Issue - State: open - Opened by abhijeet12s 3 months ago - 25 comments

#635 - 翻译设置兼容ai或本地大模型，遇到一条字幕换行的，只翻译第一行

Issue - State: open - Opened by lin16303 3 months ago - 3 comments

#634 - why after changing gemini recognition prompt it returns to default prompt automatically ?

Issue - State: open - Opened by abhijeet12s 3 months ago

#633 - please provide hugging face link or github link of f5-tts ,because to download on 123 云盘不限速第4年 you need Chinese phone number to login for 整合包部署5G(包含f5-tts模型及环境)

Issue - State: open - Opened by abhijeet12s 3 months ago - 5 comments

#632 - 想給個翻譯建議:希望多一個判斷，不要只是固定的句數送給AI翻譯，可以每次檢查一下最後一行有沒有句點或是問號或是驚嘆號

Issue - State: open - Opened by Robertchen198 3 months ago - 1 comment

#632 - 想給個翻譯建議:希望多一個判斷，不要只是固定的句數送給AI翻譯，可以每次檢查一下最後一行有沒有句點或是問號或是驚嘆號

Issue - State: open - Opened by Robertchen198 3 months ago - 1 comment

#631 - 使用自定义翻译后，合成英语音频，自动加速配音感觉好奇怪，不是听得很清

Issue - State: closed - Opened by joe12801 3 months ago

#631 - 使用自定义翻译后，合成英语音频，自动加速配音感觉好奇怪，不是听得很清

Issue - State: closed - Opened by joe12801 3 months ago

GitHub / jianchang512/pyvideotrans issues and pull requests