- Notifications
You must be signed in to change notification settings - Fork16
Auto transcribe tool based on whisper
License
tomchang25/whisper-auto-transcribe
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
- Automatically generates subtitles for video or audio content
- Translates content to English
- Supports 99 languages
- Offers high accuracy and ease of use
- Provides support for GPU acceleration and CLI mode
- Includes a one-click installer
- Increased time precision from 1 to 0.01 seconds
- Supports Youtube integration
- Preview subtitles in video
- Provides support for Background Music Mute, works fine even during heavy metal live performances
- Supports long files, 3-hour files have been tested
- Resolves the issue of subtitle repetition
- Support for batch processing.
- Subtitle editing
- Improved translation
The tool is based onOpenAI-whisper, the latest project developed by OpenAI.
For more details, you can checkthis.
Clone the repo
# Chage currently dir to Document# You can specify directory to any other location except "Program Files" and "Program Files (x86)"cd~# Stable versiongit clone https://github.com/tomchang25/whisper-auto-transcribe.gitcd whisper-auto-transcribe
Open webui.bat
Check for any errors and ensure that the final lines are correct.
Launching Web UI with arguments:Running on local URL: http://127.0.0.1:7860
Open your browser and go to
http://127.0.0.1:7860
Open
enable_venv.bat
.Now, you can use the CLI mode.
# Get help messagespython .\cli.py -h# A simple examplepython .\cli.py .\mp4\1min.mp4 --output .\tmp\123456.srt -lang ja --task translate --model large# A batch examplepython .\cli.py .\mp4 --output .\batch\--model small --model medium
- InstallCUDA
- InstallCUDNN
- Unistall CPU version Pytorch
pip uninstall torch torchvision torchaudio
- ReinstallGPU version Pytorch
# on Windowspython -m pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1+cu113 -f https://download.pytorch.org/whl/torch_stable.html
Heavy MetalWatch on Youtube
4040:53:33.590 --> 0:53:38.190From the depths of hellish silence, bastard spells, explosive violence(From the depths of hell in silence, Cast their spells, explosive violence)4050:53:38.670 --> 0:53:43.190Russian minds have my protected, glorious mission undetected(Russian night time flight perfected, Flawless vision, undetected)4060:53:44.190 --> 0:53:48.190Put down in all the flames, I'm going strong, I'm half-moon's number one(Pushing on and on, their planes are going strong, Air Force number one)4070:53:49.110 --> 0:53:53.030Talking with the moon, looking for the truth, I'm moon's number one(Somewhere down below they're looking for the foe, Bomber's on the run)4080:53:53.870 --> 0:53:58.190You can hide, you can move, just to write, learn to expect, learn to think dark(You can't hide, you can't move, just abide, Their attack's been proved (raiders in the dark))4090:53:59.110 --> 0:54:03.190Silence is the night, the witch is in the fight, never miss the mark(Silent through the night the witches join the fight. Never miss their mark)4100:54:04.150 --> 0:54:08.090Canvas, wings of death, the pattern is your fate(Canvas wings of death, Prepare to meet your fate)4110:54:09.190 --> 0:54:13.030Night on the regiment, 188(Night Bomber Regiment, 588)4120:54:14.190 --> 0:54:19.090Undetected, unexpected, wings of glory, tell the story(Undetected, unexpected, Wings of glory, Tell their story)4130:54:19.530 --> 0:54:24.110Deviation, deviation, undetected, stealth, perfected(Aviation, deviation, Undetected, Stealth perfected)4140:54:24.330 --> 0:54:28.150Silence in ground, retreated to the sound, helpless in the air(Foes are losing ground, retreating to the sound, Death is in the air)4150:54:29.130 --> 0:54:33.150Suddenly appears, the world in your face, mindful, the witch is there(Suddenly appears, confirming all your fears, Strike from witches lair)4160:54:33.830 --> 0:54:36.850Let it fall, come around, I don't sound so, we're about to drown(Target found, come around, barrels sound, From the battleground)4170:54:37.210 --> 0:54:41.210Lashes, standing high, the old genie awaits, the beaten at the gates(Rodina awaits, defeat them at the gates, Live to fight and fly)4180:54:41.790 --> 0:54:43.430Just to fight and fly()4190:54:44.250 --> 0:54:48.190Canvas, wings of death, the pattern is your fate(Canvas wings of death, Prepare to meet your fate)4200:54:49.270 --> 0:54:53.070Night on the regiment, 188(Night Bomber Regiment, 588)4210:54:54.190 --> 0:54:59.110Undetected, unexpected, wings of glory, tell the story(Undetected, unexpected, Wings of glory, Tell their story)4220:54:59.470 --> 0:55:04.110Deviation, deviation, undetected, stealth, perfected(Aviation, deviation, Undetected, Stealth perfected)4230:55:24.140 --> 0:55:27.410Beneath the starlight of the heavens(Beneath the starlight of the heavens)4240:55:29.200 --> 0:55:31.720Unlikely heroes in disguise(Unlikely heroes in the skies)4250:55:31.720 --> 0:55:34.040Canvas, wings of death, the witch is gonna die(Canvas wings of death, Prepare to meet your fate)4260:55:34.660 --> 0:55:37.320Stay in fear, humble horizon(As they appear on the horizon)4270:55:39.540 --> 0:55:43.460Win when wisdom, and the night witch has come(The wind will whisper when the Night Witches come)4280:55:44.460 --> 0:55:48.560Undetected, unexpected, wings of glory, tell the story(Undetected, unexpected, Wings of glory, Tell their story)4290:55:49.480 --> 0:55:53.540Deviation, deviation, undetected, stealth, perfected(Aviation, deviation, undetected, Stealth perfected)4300:55:54.340 --> 0:55:58.140From the depths of hell in silence, lost in spells, explosive violence(From the depths of hell in silence, Cast their spells, explosive violence)4310:55:59.260 --> 0:56:04.220Russian beta, but perfected, bonus mission, undetected(Russian night time flight perfected, Flawless vision, undetected)
EnglishWatch on Youtube
00:00:00,0 --> 0:00:10,0 The most popular is the Yashino Nakama, which stands on the shore of the Makurazaki City in Kagoshima Prefecture.10:00:11,0 --> 0:00:22,0 Makurazaki City used to be called the Typhoon Ginza, and the typhoon was approaching it frequently.20:00:22,0 --> 0:00:27,0 On Sunday, the Typhoon Ginza approached the Makurazaki City.30:00:28,0 --> 0:00:41,0 One of the four trees was named Yasshi on SNS, and there were many supportive comments.40:00:42,0 --> 0:00:44,0 Yasshi, do your best!50:00:45,0 --> 0:00:47,0 Yasshi, run away quickly!60:00:47,0 --> 0:00:51,0 Run away? If you have to, take off your roots and run away?70:00:51,0 --> 0:01:17,0 There are also voices asking to sell Yasshi goods.
Currently, there are several restrictions on this project.
- GPU acceleration only works on CUDA environment.
Also, if you want to use GPU acceleration, please make sure you have enough GPU VRAM.Here is some recommended value.
Precision | Whisper model | Required VRAM | *Time used | Performance |
---|---|---|---|---|
1 | tiny | ~1 GB | ~1/20 | ~Disaster |
2 | base | ~1 GB | ~1/10 | ~Youtube |
3 | small | ~2 GB | ~1/8 | - |
4 | medium | ~5 GB | ~1/5 | - |
5 | large | ~10 GB | ~1/2 | ~Sonix.ai |
*Time used is relatived to video/audio time and test in 10 min Enlgish audio with GPU acceleration.
Report Bugs:https://github.com/tomchang25/whisper-auto-transcribe/issues
Project Link:https://github.com/tomchang25/whisper-auto-transcribe
My twitter:https://twitter.com/Greysuki
My Gmail:tomchang25@gmail.com
The code and the model weights of Whisper are released under the MIT License.
This project is distributed under the MIT License. Please refer toLICENSE.txt
for more information.
About
Auto transcribe tool based on whisper
Topics
Resources
License
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Uh oh!
There was an error while loading.Please reload this page.