Comments (6)
@1353604736 Windows is usually fine sharing hardware resources between multiple running processes. And I think when the issue is interference with other running processes, the symptoms should be different. For CPU load, it’s just slow down. For GPU load one possible symptom is TDR timeout, like DXGI_ERROR_DEVICE_REMOVED
code from some GPU API method.
Might be a bug somewhere.
Can you upload or link the audio you’re processing?
from whisper.
@1353604736 Windows is usually fine sharing hardware resources between multiple running processes. And I think when the issue is interference with other running processes, the symptoms should be different. For CPU load, it’s just slow down. For GPU load one possible symptom is TDR timeout, like
DXGI_ERROR_DEVICE_REMOVED
code from some GPU API method.Might be a bug somewhere. Can you upload or link the audio you’re processing?
Similar issue found: ggerganov/whisper.cpp#471
许老脉诊12_MP3.zip
from whisper.
mp3 file to reproduce the problem
张震号脉01_0002_MP3.zip
from whisper.
@Const-me, looking through whisper.cpp issues it seems like a lot of people solved this repeated/duplicated lines problem by adjusting the entropy threshold. For example:
ggerganov/whisper.cpp#471 (comment)
ggerganov/whisper.cpp#508 (comment)
I'm wondering if there would maybe be a way to give access to the --entropy-thold
value within your GUI.
For me, even using version 1.7, I still get endless repetitions in almost anything I try that's not English. If I split it into small enough chunks I can get it to work, but eventually it breaks down. Sometimes it recovers, and starts working, but then inevitably it will start duplicating lines again.
Here's an Italian test file example with the model set to medium.bin
and the language set to Italian
where at 2:24
it just starts saying Grazie.
over and over:
Switching the model to large.bin
results in a similar behavior, except this time starting at 2:33
it just starts repeating [Musica]
over and over and never recovers:
Using tiny
gives a similar problem, but it eventually starts repeating Ma la mia guarda
for the final 2+ minutes:
I originally tested this with a WAV file, but switched to an MP3 and redid all my tests so the filesize would be small enough to post to Github.
from whisper.
I have been experiencing a lot more of these issues on the newer version of WhisperDesktop. Lot's of "[BLANK], [INAUDIBLE], [COUGH]", and lots and lots of Okays repeating. Reverting to a release I downloaded on 02-14 solves this.
from whisper.
I see this issue again even after downgrading - maybe something went wrong when I updated my drivers. 7900 XTX on adrenalin 23.3.1. At some point I will try it in Linux with Wine and report back.
from whisper.
Related Issues (20)
- Can multiple video files be translated in batches? HOT 1
- in what case the Whisper will output an empty srt file? HOT 2
- Get GGML binary format
- Whisper stuck HOT 26
- ANY NEW UPDATE PLEASE HOT 2
- hope support arguments :--initial_prompt and batch... HOT 2
- Add support for decrypting YouTube videos via ffmpeg
- 是否可以支持音视频文件直接拖拽加载到transcribe file? HOT 1
- a Exception about "shaderData-Debug.inl":No such file or directory HOT 2
- codepage
- The CPU reference implementation doesn’t support streaming
- ERROR: The application was unable to start correctly HOT 1
- It's this software abandonware? HOT 1
- Code cannot be compiled HOT 2
- Batch Processing failed HOT 2
- The translate feature translates speech to English. It’s not available when the audio language is already English. HOT 2
- Unable to transcribe audio with the desktop app HOT 1
- Please add a minimization feature
- Issues with Loading model bin File into Model HOT 1
- 版本显示错误
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 whisper.