Comments (3)
A few more details:
-- I had extracted features using Kaldi and set them up using the instructions provided.
-- I changed gelu to torch.nn.functional.gelu
-- using torch.nn.LayerNorm as TransformerLayerNorm
Since I could get the mel-160 features to work with the above changes, I don't think this should be the reason why filterbank features are not working.
--Apoorv
from s3prl.
Hi,
The value of loss depends on the feature, hence loss computed from fbank is different then loss computed from mel-160.
The reason why you did bad on the Montreal-phone set is the following:
The fbank features are pre-processed with a stride of 10 (a.k.a a fbank vector for every 10 ms, a default of Kaldi), which does not match the phone alignment labels of the Montreal-phone set.
On the other hand, the mel-160 feature matches the duration of the Montreal-phone set, that's why you obtained reasonable results when pretrain using mel-160 features.
You should either evaluate with the cpc phone task (suggested approach), or change the parameters in preprocess_alignment.py to generate a phone label for every 10 ms (a more complicated approach).
I have verified that pre-training with fbank and evaluating with the cpc task can yield reasonable result (65.9% linear classification accuracy), pre-training with fbank feature is guaranteed to work. You only have to confirm your phone label.
I hope this helps!
from s3prl.
Hi,
Thank you for the clarification. After changing to cpc-phone set, I get the mentioned classification accuracy.
I will close the issue.
Thanks,
Apoorv
from s3prl.
Related Issues (20)
- ValueError: mutable default <class 's3prl.upstream.roberta.roberta_model.EncDecBaseConfig'> for field encoder is not allowed: use default_factory HOT 3
- Not able to submit the results. HOT 4
- The rules for conformity for emotion recognition. HOT 5
- Potential SpecAug Issue HOT 1
- What is the accept rate in the VC task evaluation output? HOT 1
- a question about two-stage downstream task HOT 1
- ASVspoof Dateset Support HOT 2
- Requesting to add CLSRIL-23 pretrained model as new upstream HOT 6
- Cannot submit my results in the leaderboard HOT 4
- Document link broken HOT 1
- Broken link HOT 4
- How to extract weighted sum SSL representations from an audio dataset?
- 使用自己的数据进行预训练
- run vq_apc pretrain failed HOT 3
- QbE downstream HOT 3
- Performance difference between converted models and official models HOT 1
- A way to save and load the output of upstream model for speedup HOT 1
- Adding MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations (https://arxiv.org/pdf/2406.05661) HOT 1
- Can't load local checkpoint
- [Deleted]
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 s3prl.