Const-me/Whisper issues and pull requests

#224 - Allow for file drag and drop

Pull Request - State: open - Opened by realazizk about 1 month ago

#223 - Implementing Audible Captions

Issue - State: open - Opened by tom-huntington about 1 month ago

#222 - 版本显示错误

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

#221 - Language codes are defined in whisper.cpp

Pull Request - State: open - Opened by gqqnbig about 2 months ago

#220 - Issues with Loading model bin File into Model

Issue - State: open - Opened by jasonsu123 3 months ago - 2 comments

#219 - Please add a minimization feature

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

#218 - Unable to transcribe audio with the desktop app

Issue - State: open - Opened by search620 4 months ago - 1 comment

#217 - The translate feature translates speech to English. It’s not available when the audio language is already English.

Issue - State: open - Opened by lzy100p 5 months ago - 2 comments

#216 - Batch Processing failed

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

#215 - Code cannot be compiled

Issue - State: open - Opened by dfengpo 6 months ago - 2 comments

#214 - It's this software abandonware?

Issue - State: open - Opened by klonte 6 months ago - 1 comment

#213 - ERROR: The application was unable to start correctly

Issue - State: open - Opened by slishnevsky 6 months ago - 3 comments

#212 - The CPU reference implementation doesn’t support streaming

Issue - State: open - Opened by 276585877 6 months ago

#211 - codepage

Issue - State: open - Opened by 0142929 7 months ago

#210 - a Exception about "shaderData-Debug.inl":No such file or directory

Issue - State: closed - Opened by wangtao7611 7 months ago - 2 comments

#209 - 是否可以支持音视频文件直接拖拽加载到transcribe file？

Issue - State: open - Opened by xxtcc 7 months ago - 1 comment

#208 - Add support for decrypting YouTube videos via ffmpeg

Issue - State: open - Opened by Koaxz 7 months ago

#207 - hope support arguments :--initial_prompt and batch...

Issue - State: open - Opened by lforlgg 7 months ago - 2 comments

#206 - ANY NEW UPDATE PLEASE

Issue - State: open - Opened by chensuser 7 months ago - 2 comments

#205 - Whisper stuck

Issue - State: open - Opened by eagerly-learn 8 months ago - 26 comments

#204 - Get GGML binary format

Issue - State: open - Opened by SunnyPage 8 months ago

#203 - in what case the Whisper will output an empty srt file?

Issue - State: open - Opened by lpf1143 8 months ago - 2 comments

#202 - Can multiple video files be translated in batches?

Issue - State: open - Opened by Markreisen 8 months ago - 1 comment

#201 - Unable to load the model

Issue - State: open - Opened by f5c112 8 months ago - 3 comments

#200 - 如何转录系统扬声器的声音而不是系统麦克风？

Issue - State: open - Opened by Idealisten 8 months ago - 6 comments

#199 - Some questions regarding the updates and model of the WhisperDesktop package?

Issue - State: open - Opened by jasonsu123 8 months ago

#198 - mint

Issue - State: closed - Opened by jamesxie1314 9 months ago

#197 - Add new feature.

Issue - State: closed - Opened by YanFeiChina 9 months ago - 2 comments

#196 - 流号码无效

Issue - State: open - Opened by 1972074121 10 months ago - 2 comments

#195 - Computer shuts down after a while

Issue - State: open - Opened by Rhb-4 10 months ago - 4 comments

#194 - [Help!] Is that Whisper just support to output the spoken language of Chinese (Cantonese)?

Issue - State: closed - Opened by EkoWong 10 months ago

#193 - The program (cli) does not work when using the option "offset" is used.

Issue - State: open - Opened by JeanCaro 10 months ago

#192 - Original whisper cpp now as fast as const-me version

Issue - State: open - Opened by emcodem 10 months ago - 8 comments

#191 - trancribe long text without punctuation

Issue - State: open - Opened by gkngkngkn 10 months ago - 1 comment

#190 - runFullImpl: failed to generate timestamp token - skipping one second while using ggml-large-v3_2

Issue - State: open - Opened by awaqawaqawaq 11 months ago - 9 comments

#189 - add multiple gpus support

Issue - State: open - Opened by alighamdan 11 months ago - 2 comments

#188 - plz support the latest Large V3 model

Issue - State: open - Opened by MrFutureV 11 months ago - 23 comments

#187 - distil-large support request.

Issue - State: open - Opened by AeneasZhu 11 months ago - 2 comments

#186 - used works but after a recovery from a windows restore point, it stop working: attribute was not found.

Issue - State: closed - Opened by rsyqvthv 11 months ago - 1 comment

#185 - The results are correctly output in the Debug Console, but the green progress bar is stuck at the end.

Issue - State: open - Opened by ASH521 12 months ago - 5 comments

#184 - Hi, i would like receive GPU recommendations for Large and Medium Models to run in AMD, Intel or Nvidia.

Issue - State: open - Opened by Whisper-Padawan 12 months ago - 5 comments

#183 - Cant load ggml-base.en-q5_1.bin model

Issue - State: open - Opened by bilalazhar72 12 months ago - 1 comment

#182 - How to set output srt file path via cli?

Issue - State: open - Opened by ourcubk 12 months ago - 1 comment

#181 - Capture Audio and save the audio as wav/mp3 file feature suggestion

Issue - State: open - Opened by JackyWay 12 months ago - 1 comment

#180 - Prompt?

Issue - State: open - Opened by Quidam2k 12 months ago - 3 comments

#179 - GPU Recommendation

Issue - State: open - Opened by RickArcher108 about 1 year ago - 6 comments

#178 - main.exe language Ukrainian outputs only ???? (this is not the colorize issue)

Issue - State: open - Opened by emcodem about 1 year ago - 1 comment

#177 - Wine (Linux): Transcribe failed Error code -1072868846 (0xC00D5212)

Issue - State: open - Opened by faveoled about 1 year ago - 2 comments

#176 - MF.dll was not found

Issue - State: open - Opened by faveoled about 1 year ago - 1 comment

#175 - Add OpenVINO support from Whisper.cpp

Issue - State: open - Opened by NikosDi about 1 year ago

#174 - I want to process multiple files with WhisperDesktop

Issue - State: closed - Opened by kbuwel about 1 year ago - 2 comments

#173 - When will there be a Mac desktop program?

Issue - State: closed - Opened by everfu about 1 year ago - 5 comments

#172 - Use Whisper from CMD

Issue - State: open - Opened by amichelis about 1 year ago - 12 comments

#171 - English translation

Issue - State: open - Opened by RickArcher108 about 1 year ago - 1 comment

#170 - (0xc0000142).

Issue - State: open - Opened by Rain-Of-Stars about 1 year ago - 1 comment

#169 - Whisper on Proton/Wine

Issue - State: closed - Opened by adamreed90 about 1 year ago - 1 comment

#168 - Hello, where can I download Whisper desktop-specific models?

Issue - State: open - Opened by jasonsu123 about 1 year ago - 1 comment

#167 - Sample code for WhisperNet?

Issue - State: closed - Opened by ihavegoodnameiscool about 1 year ago - 2 comments

#166 - Support for whisper-large-v2?

Issue - State: open - Opened by CharreyW about 1 year ago - 2 comments

#165 - There is a problem with Japanese translation and dictation

Issue - State: open - Opened by kbuwel about 1 year ago - 1 comment

#164 - main.exe hang forever when cmd line is faulty

Issue - State: closed - Opened by emcodem about 1 year ago - 1 comment

#163 - Can you increase support for the ggml-model-whisper-large-q5_0.bin model file?

Issue - State: open - Opened by Nicolas-Gong about 1 year ago

#162 - Batch Processing

Issue - State: open - Opened by RickArcher108 about 1 year ago - 6 comments

#161 - 请问有大神实现流式识别吗？可否分享一下代码？

Issue - State: open - Opened by WLQ0110 about 1 year ago - 6 comments

#160 - Description is misleading

Issue - State: closed - Opened by tom-huntington about 1 year ago - 1 comment

#159 - Virus False Positive?

Issue - State: open - Opened by kd0frg about 1 year ago - 3 comments

#158 - Hi, I'm new to Whisper and would like to ask some basic questions about Whisper Desktop compatibility.

Issue - State: open - Opened by Whisper-Padawan about 1 year ago - 2 comments

#157 - Feature request: Microphone audio transcribed into active window.

Issue - State: open - Opened by glinkot about 1 year ago - 8 comments

#156 - loadModel on ancient gpu

Issue - State: open - Opened by MWStefan about 1 year ago

#155 - How to send PCM Data when using whisper.dll as a library

Issue - State: closed - Opened by endink about 1 year ago - 8 comments

#154 - Which ggml version is supported?

Issue - State: open - Opened by MSDNAndi about 1 year ago - 1 comment

#153 - Is it possible to add batch extraction of video subtitles？

Issue - State: open - Opened by Zero-net-oss about 1 year ago - 7 comments

#152 - Opened the Debug Console cmd window output Chinese garbled how to do?

Issue - State: closed - Opened by fgr178707 about 1 year ago - 9 comments

#151 - GUI becomes unresponsive when loading a model

Issue - State: open - Opened by karim23657 about 1 year ago - 1 comment

#150 - Videos over 30 minutes - 2 hours long are almost impossible to translate with subtitles

Issue - State: open - Opened by yczhwei about 1 year ago - 3 comments

#149 - Request for REST API

Issue - State: open - Opened by zwilch about 1 year ago - 4 comments

#148 - Transcribing multiple audio files at once

Issue - State: open - Opened by HalloweenMagic about 1 year ago - 1 comment

#147 - Consider adopting this project's UX to allow dictating anywhere

Issue - State: closed - Opened by osnofas about 1 year ago - 2 comments

#146 - The translation repeats words from the same line multiple times.

Issue - State: open - Opened by rheydheck about 1 year ago - 10 comments

#145 - Data loss when capturing from microphone eCaptureStatus::Stalled

Issue - State: closed - Opened by emcodem about 1 year ago - 6 comments

#144 - MicrophoneCS output to txt file patch

Issue - State: closed - Opened by emcodem about 1 year ago - 1 comment

#143 - Let you know if you don't, there is a `faster whisper` than `whisper.cpp`

Issue - State: open - Opened by HaujetZhao about 1 year ago - 5 comments

#142 - How to fix a single subtitle that is too long

Issue - State: closed - Opened by supermaruko about 1 year ago - 2 comments

#141 - Ability to capture audio from YouTube, twitch, etc.. and preform live transcription and translation

Issue - State: closed - Opened by harborwater about 1 year ago - 1 comment

#140 - ----

Issue - State: closed - Opened by wzzhanghong about 1 year ago - 1 comment

#139 - Adding beam_size 3/5 for better accuracy

Issue - State: closed - Opened by DJMo13 about 1 year ago

#138 - Support .webm and .weba

Issue - State: closed - Opened by natural-harmonia-gropius about 1 year ago - 3 comments

#137 - can't download the model

Issue - State: open - Opened by Idealisten about 1 year ago - 1 comment

GitHub / Const-me/Whisper issues and pull requests