Comments (8)
Yes, the transcription time depends on the audio file duration. Long files will take longer.
from faster-whisper.
Try running the model with 8-bit quantization:
model = WhisperModel(model_path, device="cuda", compute_type="int8")
from faster-whisper.
Hi,
The Whisper transcription loop already handles long files using a sliding 30-second window while keeping the context. So you don't need to do anything to transcribe long files.
from faster-whisper.
Thank you. So is it normal that the transcription time is considerably long for long files ?
from faster-whisper.
Sorry I closed and reopened the issue. I just have one last thing about the longer files.
If we use the "gpu" as a device, is there any way we can avoid OOM for these longer files ?
from faster-whisper.
What is your GPU and what model size are you running?
from faster-whisper.
It's a NVIDIA GeForce GTX 1070 Ti 8Go, I was running the large-v2 model on a 18min file. But even with 4min file I have OOM.
from faster-whisper.
Wow, just like that! it's a lot faster, and no OOM!!!
Thank you!
I will close the issue now for good :)
from faster-whisper.
Related Issues (20)
- Batch process available? HOT 2
- Word-level timestamps are off after hotwords is setted HOT 1
- Finetuning with Dora HOT 1
- Is there a method or parameter that can filter out noise that is not human voice? HOT 3
- The VAD parameters and default values in the source code is inconsistent with the description in README.md HOT 1
- how can I get more accurate timestamps? HOT 1
- Can not upload model to hub HOT 1
- TypeError: `pad_width` must be of integral type. HOT 3
- Minimum CUDA version HOT 1
- 有没有大佬遇到过 a problem RuntimeError: Cannot load the vocabulary from the model directory HOT 1
- Transcribe results being translated to different language HOT 11
- Local or remote? HOT 1
- issue with GPU utilization, RTX 3060 mobile, CUDA 12. HOT 2
- Question regarding avg_logprobability HOT 1
- distil-large-v3 is fast but exports wrong language / large-v3 is slow HOT 4
- Whisper invalid input feartures shape. HOT 2
- is their any example for onnx HOT 1
- Transcribe outputs gibberish english even when language param is set HOT 2
- ValueError: Input audio chunk is too short when transcribing numpy array HOT 3
- How to choose the CUDA 12 version? Can it support CUDA 12.2? HOT 1
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.