Comments (3)
Yes, that's the last resort. That will be very slow because every time you infer using the acoustic model. With DS2's grid search, they freeze the logits and just search over the LM params, making the thing a lot faster. I was wondering if we can do something like that here.
from self-supervised-speech-recognition.
You can prepare a test set and perform a simple grid search for hyperparameter tuning
from self-supervised-speech-recognition.
I also meet this issue
from self-supervised-speech-recognition.
Related Issues (20)
- How to disable shuffle in wav2vec during inference
- Strange characters prediction
- how to do lexicon free decoding
- Issue while fine-tuning the wav2vec model
- Wav2vec-U
- how to train from scratch wav2vec + wav2letter
- Install dependencies in CentOS
- Train on noisy audio
- finetune.py does not save checkpoints HOT 1
- memory leak with stt.py HOT 1
- How to predict under windows ?
- Any alternative way of installing apt-get packages? HOT 1
- audio segmentation HOT 1
- Some Problems about install your model HOT 1
- wav2letter install problem at Colab HOT 4
- How to use another pretrained model .pth to finetune if I really want to use this model ?
- test WER HOT 1
- How to use kenlm language model
- stt
- error install wav2letter HOT 3
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 self-supervised-speech-recognition.