Comments (8)
Large-v3 model hallucinates, large-v2 doesn't
It's known that large-v3 hallucinates much more than large-v2, read there:
Whisper-v3 Hallucinations on Real World Data
from faster-whisper.
@Arche151 , could you try again with compute_type="default" (or remove this command when initializing whisper model) ?
from faster-whisper.
@Arche151 , could you try again with compute_type="default" (or remove this command when initializing whisper model) ?
Thanks for the quick reply and suggestion!
I'll try that and report back.
from faster-whisper.
Large-v3 model hallucinates, large-v2 doesn't
It's known that large-v2 hallucinates much more that large-v2, read there: Whisper-v3 Hallucinations on Real World Data
Damn, that sucks hard. In that case, there's ofc nothing that faster-whisper can change about that. Then I guess I'll stay with large-v2.
Thanks for linking the article!
from faster-whisper.
Then I guess I'll stay with large-v3.
Did you meant "large-v2"?
On my Standalone Faster-Whisper I've added auto-offsets to whisper's pseudo-vad thresholds when "v3" is in use, you can try these parameters when using large-v3:
compression_ratio_threshold=2.2
log_prob_threshold=-0.7
from faster-whisper.
Then I guess I'll stay with large-v3.
Did you meant "large-v2"?
On my Standalone Faster-Whisper I've added auto-offsets to whisper's pseudo-vad thresholds when "v3" is in use, you can try these parameters when using large-v3:
compression_ratio_threshold=2.2
log_prob_threshold=-0.7
does it yield better result than large-v2 using your parameters with large-v3?
from faster-whisper.
Then I guess I'll stay with large-v3.
Did you meant "large-v2"?
On my Standalone Faster-Whisper I've added auto-offsets to whisper's pseudo-vad thresholds when "v3" is in use, you can try these parameters when using large-v3:
compression_ratio_threshold=2.2
log_prob_threshold=-0.7
does it yield better result than large-v2 using your parameters with large-v3?
I didn't try for long enough to be able to say. Just went back to large-v2 after reading the deepgram article.
from faster-whisper.
does it yield better result than large-v2 using your parameters with large-v3?
You tell me, as I don't use large-v3. IMO large-v2 is better.
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 8
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.