Comments (9)
The same error was reported in #12 (comment) but I was not able to reproduce it.
Can you share an audio file that produces this error?
from faster-whisper.
I'm afraid i can't send you the audio because it is copyrighted material. However, I can provide you with more details. I've noticed that this error consistently occurs at the end of the audio.
from faster-whisper.
To confirm I independently get the same error at the end of audio. I also can't share the audio. Note that I get it non deterministically, some times it's fine and ends with a final word of a... or a.
from faster-whisper.
Here's the content of jump_times
and word_boundaries
when this error occurs:
# jump_times
[0.]
# word_boundaries
[ 0 1 4 5 6 7 8 9 10 13 16 17 18 19 20 21 22 23 24 25 28 29 32 33
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 51 54 55 56 57 58 59 60 61
62 63 66]
from faster-whisper.
Does the same file run without errors when using word-level timestamps in openai/whisper?
Also what model size are you using?
from faster-whisper.
Yes, it can run normally in original whisper. I'm using large-v2
model
from faster-whisper.
Thanks for the info.
I found the issue. There is a small error in the DTW implementation in CTranslate2: OpenNMT/CTranslate2#1136
I will release a new version soon.
from faster-whisper.
Not sure if this is helpful or not but I had a similar traceback and found out that setting without_timestamps=True
causes it to happen randomly. As soon as I set it to False, it never came back.
So yeah maybe just me being dumb setting the parameter, could be unrelated. Maybe could be caught by the library too.
Thanks for all your work btw. faster-whisper is really great!
from faster-whisper.
The error should be fixed with ctranslate2>=3.9.1
.
from faster-whisper.
Related Issues (20)
- 2 wavs file with same content generate different result HOT 4
- Problem with audio HOT 5
- How to run HOT 2
- CUDA 12 required? HOT 4
- faster-whisper docker example? HOT 2
- Word-level timestamps are off by some multiplier HOT 1
- Does it support converting to ONNX format models?
- question: client sdk HOT 1
- RuntimeError: CUDA failed with error CUDA driver version is insufficient for CUDA runtime version HOT 2
- Whisper-live taking same time on CPU and GPU to transcribe an audio HOT 4
- is it possible for customize VAD model path?
- Are timestamp tokens used in previous text?
- How do I get both transcript and translated output from single process? HOT 4
- mkl_malloc: failed to allocate memory HOT 1
- Can we modify vocabulary
- change subtitles lenght per line HOT 1
- Allow loading model from memory HOT 6
- Long video processing failure without error HOT 2
- transcribe can't find files outside current script working directory HOT 4
- no kernel image is available for execution on the device HOT 4
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 faster-whisper.